%%% -*-BibTeX-*-
%%% ====================================================================
%%% BibTeX-file{
%%%     author          = "Nelson H. F. Beebe",
%%%     version         = "1.28",
%%%     date            = "13 March 2014",
%%%     time            = "09:52:58 MST",
%%%     filename        = "tslp.bib",
%%%     address         = "University of Utah
%%%                        Department of Mathematics, 110 LCB
%%%                        155 S 1400 E RM 233
%%%                        Salt Lake City, UT 84112-0090
%%%                        USA",
%%%     telephone       = "+1 801 581 5254",
%%%     FAX             = "+1 801 581 4148",
%%%     URL             = "http://www.math.utah.edu/~beebe",
%%%     checksum        = "59680 3346 16986 163849",
%%%     email           = "beebe at math.utah.edu, beebe at acm.org,
%%%                        beebe at computer.org (Internet)",
%%%     codetable       = "ISO/ASCII",
%%%     keywords        = "ACM Transactions on Speech and Language
%%%                        Processing (TSLP); BibTeX; bibliography",
%%%     license         = "public domain",
%%%     supported       = "yes",
%%%     docstring       = "This is a COMPLETE BibTeX bibliography for
%%%                        ACM Transactions on Speech and Language
%%%                        Processing (TSLP) (CODEN ????, ISSN
%%%                        1550-4875), covering all journal issues from
%%%                        2004 -- date.
%%%
%%%                        At version 1.28, the COMPLETE journal
%%%                        coverage looked like this:
%%%
%%%                             2004 (   1)    2008 (   3)    2012 (   8)
%%%                             2005 (   5)    2009 (   2)    2013 (  23)
%%%                             2006 (   7)    2010 (   3)
%%%                             2007 (  12)    2011 (  21)
%%%
%%%                             Article:         85
%%%
%%%                             Total entries:   85
%%%
%%%                        The journal Web page can be found at:
%%%
%%%                            http://www.acm.org/pubs/tslp/
%%%                            http://portal.acm.org/browse_dl.cfm?&idx=J957
%%%
%%%                        Qualified subscribers can retrieve the full
%%%                        text of recent articles in PDF form.
%%%
%%%                        The initial draft was extracted from the ACM
%%%                        Web pages.
%%%
%%%                        ACM copyrights explicitly permit abstracting
%%%                        with credit, so article abstracts, keywords,
%%%                        and subject classifications have been
%%%                        included in this bibliography wherever
%%%                        available.  Article reviews have been
%%%                        omitted, until their copyright status has
%%%                        been clarified.
%%%
%%%                        bibsource keys in the bibliography entries
%%%                        below indicate the entry originally came
%%%                        from the computer science bibliography
%%%                        archive, even though it has likely since
%%%                        been corrected and updated.
%%%
%%%                        URL keys in the bibliography point to
%%%                        World Wide Web locations of additional
%%%                        information about the entry.
%%%
%%%                        BibTeX citation tags are uniformly chosen
%%%                        as name:year:abbrev, where name is the
%%%                        family name of the first author or editor,
%%%                        year is a 4-digit number, and abbrev is a
%%%                        3-letter condensation of important title
%%%                        words. Citation tags were automatically
%%%                        generated by software developed for the
%%%                        BibNet Project.
%%%
%%%                        In this bibliography, entries are sorted in
%%%                        publication order, using ``bibsort -byvolume.''
%%%
%%%                        The checksum field above contains a CRC-16
%%%                        checksum as the first value, followed by the
%%%                        equivalent of the standard UNIX wc (word
%%%                        count) utility output of lines, words, and
%%%                        characters.  This is produced by Robert
%%%                        Solovay's checksum utility."
%%%     }
%%% ====================================================================

@Preamble{"\input bibnames.sty"}

%%% ====================================================================
%%% Acknowledgement abbreviations:

@String{ack-nhfb = "Nelson H. F. Beebe,
                    University of Utah,
                    Department of Mathematics, 110 LCB,
                    155 S 1400 E RM 233,
                    Salt Lake City, UT 84112-0090, USA,
                    Tel: +1 801 581 5254,
                    FAX: +1 801 581 4148,
                    e-mail: \path|beebe@math.utah.edu|,
                            \path|beebe@acm.org|,
                            \path|beebe@computer.org| (Internet),
                    URL: \path|http://www.math.utah.edu/~beebe/|"}

%%% ====================================================================
%%% Journal abbreviations:

@String{j-TSLP                  = "ACM Transactions on Speech and Language
                                  Processing (TSLP)"}

%%% ====================================================================
%%% Bibliography entries:

@Article{Higashinaka:2004:EDU,
  author =       "Ryuichiro Higashinaka and Noboru Miyazaki and Mikio
                 Nakano and Kiyoaki Aikawa",
  title =        "Evaluating discourse understanding in spoken dialogue
                 systems",
  journal =      j-TSLP,
  volume =       "1",
  number =       "1",
  pages =        "1--20",
  month =        nov,
  year =         "2004",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1035112.1035113",
  ISSN =         "1550-4875",
  bibdate =      "Mon Nov 22 07:30:52 MST 2004",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Verma:2005:VFI,
  author =       "Ashish Verma and Arun Kumar",
  title =        "Voice fonts for individuality representation and
                 transformation",
  journal =      j-TSLP,
  volume =       "2",
  number =       "1",
  pages =        "1--19",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Fri Nov 18 08:15:59 MST 2005",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Koumpis:2005:ASV,
  author =       "Konstantinos Koumpis and Steve Renals",
  title =        "Automatic summarization of voicemail messages using
                 lexical and prosodic features",
  journal =      j-TSLP,
  volume =       "2",
  number =       "1",
  pages =        "1--24",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Fri Nov 18 08:15:59 MST 2005",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Tomko:2005:TEH,
  author =       "Stefanie Tomko and Thomas K. Harris and Arthur Toth
                 and James Sanders and Alexander Rudnicky and Roni
                 Rosenfeld",
  title =        "Towards efficient human machine speech communication:
                 {The} speech graffiti project",
  journal =      j-TSLP,
  volume =       "2",
  number =       "1",
  pages =        "1--27",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Fri Nov 18 08:15:59 MST 2005",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Lapata:2005:WBM,
  author =       "Mirella Lapata and Frank Keller",
  title =        "{Web}-based models for natural language processing",
  journal =      j-TSLP,
  volume =       "2",
  number =       "1",
  pages =        "1--31",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Fri Nov 18 08:15:59 MST 2005",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Federico:2005:WPS,
  author =       "Marcello Federico and Nicola Bertoldi",
  title =        "A word-to-phrase statistical translation model",
  journal =      j-TSLP,
  volume =       "2",
  number =       "2",
  pages =        "1--24",
  month =        dec,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Thu Feb 16 11:43:49 MST 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Avancini:2006:AED,
  author =       "Henri Avancini and Alberto Lavelli and Fabrizio
                 Sebastiani and Roberto Zanoli",
  title =        "Automatic expansion of domain-specific lexicons by
                 term categorization",
  journal =      j-TSLP,
  volume =       "3",
  number =       "1",
  pages =        "1--30",
  month =        may,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Wed Jun 14 10:17:29 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Fung:2006:OSO,
  author =       "Pascale Fung and Grace Ngai",
  title =        "One story, one flow: {Hidden Markov Story Models} for
                 multilingual multidocument summarization",
  journal =      j-TSLP,
  volume =       "3",
  number =       "2",
  pages =        "1--16",
  month =        jul,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Wed Nov 15 06:40:22 MST 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Wang:2006:HQS,
  author =       "Chao Wang and Stephanie Seneff",
  title =        "High-quality speech-to-speech translation for
                 computer-aided language learning",
  journal =      j-TSLP,
  volume =       "3",
  number =       "2",
  pages =        "1--21",
  month =        jul,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Wed Nov 15 06:40:22 MST 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Ma:2006:AEC,
  author =       "Ling Ma and Ben Milner and Dan Smith",
  title =        "Acoustic environment classification",
  journal =      j-TSLP,
  volume =       "3",
  number =       "2",
  pages =        "1--22",
  month =        jul,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Wed Nov 15 06:40:22 MST 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Sporleder:2006:BCP,
  author =       "Caroline Sporleder and Mirella Lapata",
  title =        "Broad coverage paragraph segmentation across languages
                 and domains",
  journal =      j-TSLP,
  volume =       "3",
  number =       "2",
  pages =        "1--35",
  month =        jul,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Wed Nov 15 06:40:22 MST 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Gandrabur:2006:CEN,
  author =       "Simona Gandrabur and George Foster and Guy Lapalme",
  title =        "Confidence estimation for {NLP} applications",
  journal =      j-TSLP,
  volume =       "3",
  number =       "3",
  pages =        "1--29",
  month =        oct,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Wed Nov 15 06:39:00 MST 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Hakkani-Tur:2006:AAS,
  author =       "Dilek Hakkani-T{\"u}r and Giuseppe Riccardi and Gokhan
                 Tur",
  title =        "An active approach to spoken language processing",
  journal =      j-TSLP,
  volume =       "3",
  number =       "3",
  pages =        "1--31",
  month =        oct,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Wed Nov 15 06:39:00 MST 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{VanHalteren:2007:AVL,
  author =       "Hans {Van Halteren}",
  title =        "Author verification by linguistic profiling: {An}
                 exploration of the parameter space",
  journal =      j-TSLP,
  volume =       "4",
  number =       "1",
  pages =        "1:1--1:??",
  month =        jan,
  year =         "2007",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:22:59 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article explores the effects of parameter
                 settings in linguistic profiling, a technique in which
                 large numbers of counts of linguistic features are used
                 as a text profile which can then be compared to average
                 profiles for groups of texts. Although the technique
                 proves to be quite effective for authorship
                 verification, with the best overall parameter settings
                 yielding an equal error rate of 3\% on a test corpus of
                 student essays, the optimal parameters vary greatly
                 depending on author and evaluation criterion.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "Authorship attribution; authorship recognition;
                 authorship verification; machine learning",
}

@Article{Inkpen:2007:SMN,
  author =       "Diana Inkpen",
  title =        "A statistical model for near-synonym choice",
  journal =      j-TSLP,
  volume =       "4",
  number =       "1",
  pages =        "2:1--2:??",
  month =        jan,
  year =         "2007",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:22:59 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We present an unsupervised statistical method for
                 automatic choice of near-synonyms when the context is
                 given. The method uses the Web as a corpus to compute
                 scores based on mutual information. Our evaluation
                 experiments show that this method performs better than
                 two previous methods on the same task. We also describe
                 experiments in using supervised learning for this task.
                 We present an application to an intelligent thesaurus.
                 This work is also useful in machine translation and
                 natural language generation.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "intelligent thesaurus; Lexical choice; near-synonyms;
                 semantic similarity; Web as a corpus",
}

@Article{Creutz:2007:UMM,
  author =       "Mathias Creutz and Krista Lagus",
  title =        "Unsupervised models for morpheme segmentation and
                 morphology learning",
  journal =      j-TSLP,
  volume =       "4",
  number =       "1",
  pages =        "3:1--3:??",
  month =        jan,
  year =         "2007",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:22:59 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We present a model family called Morfessor for the
                 unsupervised induction of a simple morphology from raw
                 text data. The model is formulated in a probabilistic
                 maximum a posteriori framework. Morfessor can handle
                 highly inflecting and compounding languages where words
                 can consist of lengthy sequences of morphemes. A
                 lexicon of word segments, called morphs, is induced
                 from the data. The lexicon stores information about
                 both the usage and form of the morphs. Several
                 instances of the model are evaluated quantitatively in
                 a morpheme segmentation task on different sized sets of
                 Finnish as well as English data. Morfessor is shown to
                 perform very well compared to a widely known benchmark
                 algorithm, in particular on Finnish data.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "Efficient storage; highly inflecting and compounding
                 languages; language independent methods; maximum a
                 posteriori (MAP) estimation; morpheme lexicon and
                 segmentation; unsupervised learning",
}

@Article{Nenkova:2007:PMI,
  author =       "Ani Nenkova and Rebecca Passonneau and Kathleen
                 McKeown",
  title =        "The {Pyramid Method}: {Incorporating} human content
                 selection variation in summarization evaluation",
  journal =      j-TSLP,
  volume =       "4",
  number =       "2",
  pages =        "4:1--4:??",
  month =        may,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1233912.1233913",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:08 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Human variation in content selection in summarization
                 has given rise to some fundamental research questions:
                 How can one incorporate the observed variation in
                 suitable evaluation measures? How can such measures
                 reflect the fact that summaries conveying different
                 content can be equally good and informative? In this
                 article, we address these very questions by proposing a
                 method for analysis of multiple human abstracts into
                 semantic content units. Such analysis allows us not
                 only to quantify human variation in content selection,
                 but also to assign empirical importance weight to
                 different content units. It serves as the basis for an
                 evaluation method, the Pyramid Method, that
                 incorporates the observed variation and is predictive
                 of different equally informative summaries. We discuss
                 the reliability of content unit annotation, the
                 properties of Pyramid scores, and their correlation
                 with other evaluation methods.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "Evaluation; semantic analysis; summarization",
}

@Article{Yan:2007:CSD,
  author =       "Jiajun Yan and David B. Bracewell and Shingo Kuroiwa
                 and Fuji Ren",
  title =        "{Chinese} semantic dependency analysis: {Construction}
                 of a treebank and its use in classification",
  journal =      j-TSLP,
  volume =       "4",
  number =       "2",
  pages =        "5:1--5:??",
  month =        may,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1233912.1233914",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:08 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Semantic analysis is a standard tool in the Natural
                 Language Processing (NLP) toolbox with widespread
                 applications. In this article, we look at tagging part
                 of the Penn Chinese Treebank with semantic dependency.
                 Then we take this tagged data to train a maximum
                 entropy classifier to label the semantic relations
                 between headwords and dependents to perform semantic
                 analysis on Chinese sentences. The classifier was able
                 to achieve an accuracy of over 84\%. We then analyze
                 the errors in classification to determine the problems
                 and possible solutions for this type of semantic
                 analysis.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "Chinese; maximum entropy classification; Natural
                 language processing; semantic dependency analysis",
}

@Article{Tillmann:2007:BBP,
  author =       "Christoph Tillmann and Tong Zhang",
  title =        "A block bigram prediction model for statistical
                 machine translation",
  journal =      j-TSLP,
  volume =       "4",
  number =       "3",
  pages =        "6:1--6:??",
  month =        jul,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1255171.1255172",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "In this article, we present a novel training method
                 for a localized phrase-based prediction model for
                 statistical machine translation (SMT). The model
                 predicts block neighbors to carry out a phrase-based
                 translation that explicitly handles local phrase
                 reordering. We use a maximum likelihood criterion to
                 train a log-linear block bigram model which uses
                 real-valued features (e.g., a language model score) as
                 well as binary features based on the block identities
                 themselves (e.g., block bigram features). The model
                 training relies on an efficient enumeration of local
                 block neighbors in parallel training data. A novel
                 stochastic gradient descent (SGD) training algorithm is
                 presented that can easily handle millions of features.
                 Moreover, when viewing SMT as a block generation
                 process, it becomes quite similar to sequential natural
                 language annotation problems such as part-of-speech
                 tagging, phrase chunking, or shallow parsing. Our novel
                 approach is successfully tested on a standard
                 Arabic-English translation task using two different
                 phrase reordering models: a block orientation model and
                 a phrase-distortion model.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "machine learning; maximum entropy; Statistical machine
                 translation; stochastic gradient descent",
}

@Article{Hanna:2007:PER,
  author =       "Philip Hanna and Ian O'Neill and Craig Wootton and
                 Michael Mctear",
  title =        "Promoting extension and reuse in a spoken dialog
                 manager: {An} evaluation of the queen's communicator",
  journal =      j-TSLP,
  volume =       "4",
  number =       "3",
  pages =        "7:1--7:??",
  month =        jul,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1255171.1255173",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article describes how an object-oriented approach
                 can be applied to the architectural design of a spoken
                 language dialog system with the aim of facilitating the
                 modification, extension, and reuse of discourse-related
                 expertise. The architecture of the developed system is
                 described and a functionally similar VoiceXML system is
                 used to provide a comparative baseline across a range
                 of modification and reuse scenarios. It is shown that
                 the use of an object-oriented dialog manager can
                 provide a capable means of reusing existing discourse
                 expertise in a manner that limits the degree of
                 structural decay associated with system change.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "dialog management; Human-computer interaction; speech
                 and language processing; spoken dialog systems",
}

@Article{Higashinaka:2007:UML,
  author =       "Ryuichiro Higashinaka and Marilyn A. Walker and Rashmi
                 Prasad",
  title =        "An unsupervised method for learning generation
                 dictionaries for spoken dialogue systems by mining user
                 reviews",
  journal =      j-TSLP,
  volume =       "4",
  number =       "4",
  pages =        "8:1--8:??",
  month =        oct,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1289600.1289601",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:20 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Spoken language generation for dialogue systems
                 requires a dictionary of mappings between the semantic
                 representations of concepts that the system wants to
                 express and the realizations of those concepts.
                 Dictionary creation is a costly process; it is
                 currently done by hand for each dialogue domain. We
                 propose a novel unsupervised method for learning such
                 mappings from user reviews in the target domain and
                 test it in the restaurant and hotel domains.
                 Experimental results show that the acquired mappings
                 achieve high consistency between the semantic
                 representation and the realization and that the
                 naturalness of the realization is significantly higher
                 than the baseline.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "generation dictionary; Natural language generation;
                 spoken dialogue systems; user reviews",
}

@Article{Ringlstetter:2007:ATC,
  author =       "Christoph Ringlstetter and Klaus U. Schulz and Stoyan
                 Mihov",
  title =        "Adaptive text correction with {Web}-crawled
                 domain-dependent dictionaries",
  journal =      j-TSLP,
  volume =       "4",
  number =       "4",
  pages =        "9:1--9:??",
  month =        oct,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1289600.1289602",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:20 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "For the success of lexical text correction, high
                 coverage of the underlying background dictionary is
                 crucial. Still, most correction tools are built on top
                 of static dictionaries that represent fixed collections
                 of expressions of a given language. When treating texts
                 from specific domains and areas, often a significant
                 part of the vocabulary is missed. In this situation,
                 both automated and interactive correction systems
                 produce suboptimal results. In this article, we
                 describe strategies for crawling Web pages that fit the
                 thematic domain of the given input text. Special
                 filtering techniques are introduced to avoid pages with
                 many orthographic errors. Collecting the vocabulary of
                 filtered pages that meet the vocabulary of the input
                 text, dynamic dictionaries of modest size are obtained
                 that reach excellent coverage values. A tool has been
                 developed that automatically crawls dictionaries in the
                 indicated way. Our correction experiments with crawled
                 dictionaries, which address English and German document
                 collections from a variety of thematic fields, show
                 that with these dictionaries even the error rate of
                 highly accurate texts can be reduced, using completely
                 automated correction methods. For interactive text
                 correction, more sensible candidate sets for correcting
                 erroneous words are obtained and the manual effort is
                 reduced in a significant way. To complete this picture,
                 we study the effect when using word trigram models for
                 correction. Again, trigram models from crawled corpora
                 outperform those obtained from static corpora.",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "Adaptive techniques; dictionaries; domains; error
                 correction; Web crawling",
}

@Article{Bulyko:2007:WRL,
  author =       "Ivan Bulyko and Mari Ostendorf and Manhung Siu and Tim
                 Ng and Andreas Stolcke and {\"O}zg{\"u}r {\c{C}}etin",
  title =        "{Web} resources for language modeling in
                 conversational speech recognition",
  journal =      j-TSLP,
  volume =       "5",
  number =       "1",
  pages =        "1:1--1:25",
  month =        dec,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1322391.1322392",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:25 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article describes a methodology for collecting
                 text from the Web to match a target sublanguage both in
                 style (register) and topic. Unlike other work that
                 estimates n-gram statistics from page counts, the
                 approach here is to select and filter documents, which
                 provides more control over the type of material
                 contributing to the n-gram counts. The data can be used
                 in a variety of ways; here, the different sources are
                 combined in two types of mixture models. Focusing on
                 conversational speech where data collection can be
                 quite costly, experiments demonstrate the positive
                 impact of Web collections on several tasks with varying
                 amounts of data, including Mandarin and English
                 telephone conversations and English meetings and
                 lectures.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "Conversational speech; language modeling; Web data",
}

@Article{Giuliano:2007:REI,
  author =       "Claudio Giuliano and Alberto Lavelli and Lorenza
                 Romano",
  title =        "Relation extraction and the influence of automatic
                 named-entity recognition",
  journal =      j-TSLP,
  volume =       "5",
  number =       "1",
  pages =        "2:1--2:26",
  month =        dec,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1322391.1322393",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:25 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We present an approach for extracting relations
                 between named entities from natural language documents.
                 The approach is based solely on shallow linguistic
                 processing, such as tokenization, sentence splitting,
                 part-of-speech tagging, and lemmatization. It uses a
                 combination of kernel functions to integrate two
                 different information sources: (i) the whole sentence
                 where the relation appears, and (ii) the local contexts
                 around the interacting entities. We present the results
                 of experiments on extracting five different types of
                 relations from a dataset of newswire documents and show
                 that each information source provides a useful
                 contribution to the recognition task. Usually the
                 combined kernel significantly increases the precision
                 with respect to the basic kernels, sometimes at the
                 cost of a slightly lower recall. Moreover, we performed
                 a set of experiments to assess the influence of the
                 accuracy of named-entity recognition on the performance
                 of the relation-extraction algorithm. Such experiments
                 were performed using both the correct named entities
                 (i.e., those manually annotated in the corpus) and the
                 noisy named entities (i.e., those produced by a machine
                 learning-based named-entity recognizer). The results
                 show that our approach significantly improves the
                 previous results obtained on the same dataset.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "Information extraction; kernel methods; named-entity
                 recognition; relation extraction",
}

@Article{Creutz:2007:MBS,
  author =       "Mathias Creutz and Teemu Hirsim{\"a}ki and Mikko
                 Kurimo and Antti Puurula and Janne Pylkk{\"o}nen and
                 Vesa Siivola and Matti Varjokallio and Ebru Arisoy and
                 Murat Sara{\c{c}}lar and Andreas Stolcke",
  title =        "Morph-based speech recognition and modeling of
                 out-of-vocabulary words across languages",
  journal =      j-TSLP,
  volume =       "5",
  number =       "1",
  pages =        "3:1--3:29",
  month =        dec,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1322391.1322394",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:25 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We explore the use of morph-based language models in
                 large-vocabulary continuous-speech recognition systems
                 across four so-called morphologically rich languages:
                 Finnish, Estonian, Turkish, and Egyptian Colloquial
                 Arabic. The morphs are subword units discovered in an
                 unsupervised, data-driven way using the Morfessor
                 algorithm. By estimating n -gram language models over
                 sequences of morphs instead of words, the quality of
                 the language model is improved through better
                 vocabulary coverage and reduced data sparsity. Standard
                 word models suffer from high out-of-vocabulary (OOV)
                 rates, whereas the morph models can recognize
                 previously unseen word forms by concatenating morphs.
                 It is shown that the morph models do perform fairly
                 well on OOVs without compromising the recognition
                 accuracy on in-vocabulary words. The Arabic experiment
                 constitutes the only exception since here the standard
                 word model outperforms the morph model. Differences in
                 the datasets and the amount of data are discussed as a
                 plausible explanation.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "Egyptian Colloquial Arabic; Estonian; Finnish; Highly
                 inflecting and compounding languages; LVCSR; Morfessor;
                 morpheme; morphologically rich languages; n -gram
                 models; subword-based language modeling; Turkish",
}

@Article{Zhang:2008:CWS,
  author =       "Ruiqiang Zhang and Keiji Yasuda and Eiichiro Sumita",
  title =        "{Chinese} word segmentation and statistical machine
                 translation",
  journal =      j-TSLP,
  volume =       "5",
  number =       "2",
  pages =        "4:1--4:??",
  month =        may,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1363108.1363109",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jun 16 11:23:34 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Chinese word segmentation (CWS) is a necessary step in
                 Chinese--English statistical machine translation (SMT)
                 and its performance has an impact on the results of
                 SMT. However, there are many choices involved in
                 creating a CWS system such as various specifications
                 and CWS methods. The choices made will create a new CWS
                 scheme, but whether it will produce a superior or
                 inferior translation has remained unknown to date. This
                 article examines the relationship between CWS and SMT.
                 The effects of CWS on SMT were investigated using
                 different specifications and CWS methods. Four
                 specifications were selected for investigation: Beijing
                 University (PKU), Hong Kong City University (CITYU),
                 Microsoft Research (MSR), and Academia SINICA (AS). We
                 created 16 CWS schemes under different settings to
                 examine the relationship between CWS and SMT. Our
                 experimental results showed that the MSR's
                 specifications produced the lowest quality
                 translations. In examining the effects of CWS methods,
                 we tested dictionary-based and CRF-based approaches and
                 found there was no significant difference between the
                 two in the quality of the resulting translations. We
                 also found the correlation between the CWS F-score and
                 SMT BLEU score was very weak. We analyzed CWS errors
                 and their effect on SMT by evaluating systems trained
                 with and without these errors. This article also
                 proposes two methods for combining advantages of
                 different specifications: a simple concatenation of
                 training data and a feature interpolation approach in
                 which the same types of features of translation models
                 from various CWS schemes are linearly interpolated. We
                 found these approaches were very effective in improving
                 the quality of translations.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "Chinese word segmentation; linear integration;
                 statistical machine translation; translation model",
}

@Article{Giannakopoulos:2008:SSE,
  author =       "George Giannakopoulos and Vangelis Karkaletsis and
                 George Vouros and Panagiotis Stamatopoulos",
  title =        "Summarization system evaluation revisited: {$N$}-gram
                 graphs",
  journal =      j-TSLP,
  volume =       "5",
  number =       "3",
  pages =        "5:1--5:??",
  month =        oct,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1410358.1410359",
  ISSN =         "1550-4875",
  bibdate =      "Fri Oct 10 13:04:55 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article presents a novel automatic method
                 (AutoSummENG) for the evaluation of summarization
                 systems, based on comparing the character n-gram graphs
                 representation of the extracted summaries and a number
                 of model summaries. The presented approach is language
                 neutral, due to its statistical nature, and appears to
                 hold a level of evaluation performance that matches and
                 even exceeds other contemporary evaluation methods.
                 Within this study, we measure the effectiveness of
                 different representation methods, namely, word and
                 character n-gram graph and histogram, different n-gram
                 neighborhood indication methods as well as different
                 comparison methods between the supplied
                 representations. A theory for the a priori
                 determination of the methods' parameters along with
                 supporting experiments concludes the study to provide a
                 complete alternative to existing methods concerning the
                 automatic summary system evaluation process.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "automatic summarization; n-gram graph; summarization
                 evaluation",
}

@Article{Shiramatsu:2008:GTM,
  author =       "Shun Shiramatsu and Kazunori Komatani and K{\^o}iti
                 Hasida and Tetsuya Ogata and Hiroshi G. Okuno",
  title =        "A game-theoretic model of referential coherence and
                 its empirical verification using large {Japanese} and
                 {English} corpora",
  journal =      j-TSLP,
  volume =       "5",
  number =       "3",
  pages =        "6:1--6:??",
  month =        oct,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1410358.1410360",
  ISSN =         "1550-4875",
  bibdate =      "Fri Oct 10 13:04:55 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Referential coherence represents the smoothness of
                 discourse resulting from topic continuity and
                 pronominalization. Rational individuals prefer a
                 referentially coherent structure of discourse when they
                 select a language expression and its interpretation.
                 This is a preference for cooperation in communication.
                 By what principle do they share coherent expressions
                 and interpretations? Centering theory is the standard
                 theory of referential coherence [Grosz et al. 1995].
                 Although it is well designed on the bases of
                 first-order inference rules [Joshi and Kuhn 1979], it
                 does not embody a behavioral principle for the
                 cooperation evident in communication. Hasida [1996]
                 proposed a game-theoretic hypothesis in relation to
                 this issue. We aim to empirically verify Hasida's
                 hypothesis by using corpora of multiple languages. We
                 statistically design language-dependent parameters by
                 using a corpus of the target language. This statistical
                 design enables us to objectively absorb
                 language-specific differences and to verify the
                 universality of Hasida's hypothesis by using corpora.
                 We empirically verified our model by using large
                 Japanese and English corpora. The result proves the
                 language universality of the hypothesis.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "centering theory; corpus statistics; discourse
                 analysis; discourse salience; game theory;
                 game-theoretic pragmatics; meaning game; perceptual
                 utility; pronominalization; reference probability;
                 referential coherence",
}

@Article{Gliozzo:2009:ITC,
  author =       "Alfio Gliozzo and Carlo Strapparava and Ido Dagan",
  title =        "Improving text categorization bootstrapping via
                 unsupervised learning",
  journal =      j-TSLP,
  volume =       "6",
  number =       "1",
  pages =        "1:1--1:??",
  month =        oct,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1596515.1596516",
  ISSN =         "1550-4875",
  bibdate =      "Fri Oct 9 20:48:21 MDT 2009",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We propose a text-categorization bootstrapping
                 algorithm in which categories are described by relevant
                 seed words. Our method introduces two unsupervised
                 techniques to improve the initial categorization step
                 of the bootstrapping scheme: (i) using latent semantic
                 spaces to estimate the similarity among documents and
                 words, and (ii) the Gaussian mixture algorithm, which
                 differentiates relevant and nonrelevant category
                 information using statistics from unlabeled examples.
                 In particular, this second step maps the similarity
                 scores to class posterior probabilities, and therefore
                 reduces sensitivity to keyword-dependent variations in
                 scores. The algorithm was evaluated on two text
                 categorization tasks, and obtained good performance
                 using only the category names as initial seeds. In
                 particular, the performance of the proposed method
                 proved to be equivalent to a pure supervised approach
                 trained on 70--160 labeled documents per category.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "bootstrapping; Text categorization; unsupervised
                 machine learning",
}

@Article{Murray:2009:ESE,
  author =       "Gabriel Murray and Thomas Kleinbauer and Peter Poller
                 and Tilman Becker and Steve Renals and Jonathan Kilgour",
  title =        "Extrinsic summarization evaluation: {A} decision audit
                 task",
  journal =      j-TSLP,
  volume =       "6",
  number =       "2",
  pages =        "2:1--2:??",
  month =        oct,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1596517.1596518",
  ISSN =         "1550-4875",
  bibdate =      "Fri Oct 9 20:49:17 MDT 2009",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "In this work we describe a large-scale extrinsic
                 evaluation of automatic speech summarization
                 technologies for meeting speech. The particular task is
                 a decision audit, wherein a user must satisfy a complex
                 information need, navigating several meetings in order
                 to gain an understanding of how and why a given
                 decision was made. We compare the usefulness of
                 extractive and abstractive technologies in satisfying
                 this information need, and assess the impact of
                 automatic speech recognition (ASR) errors on user
                 performance. We employ several evaluation methods for
                 participant performance, including post-questionnaire
                 data, human subjective and objective judgments, and a
                 detailed analysis of participant browsing behavior. We
                 find that while ASR errors affect user satisfaction on
                 an information retrieval task, users can adapt their
                 browsing behavior to complete the task satisfactorily.
                 Results also indicate that users consider extractive
                 summaries to be intuitive and useful tools for browsing
                 multimodal meeting data. We discuss areas in which
                 automatic summarization techniques can be improved in
                 comparison with gold-standard meeting abstracts.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "abstraction; browsing; evaluation; extraction;
                 interfaces; Summarization",
}

@Article{Zhu:2010:CBS,
  author =       "Jingbo Zhu and Huizhen Wang and Eduard Hovy and
                 Matthew Ma",
  title =        "Confidence-based stopping criteria for active learning
                 for data annotation",
  journal =      j-TSLP,
  volume =       "6",
  number =       "3",
  pages =        "3:1--3:??",
  month =        apr,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1753783.1753784",
  ISSN =         "1550-4875",
  bibdate =      "Mon Apr 26 14:46:47 MDT 2010",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "The labor-intensive task of labeling data is a serious
                 bottleneck for many supervised learning approaches for
                 natural language processing applications. Active
                 learning aims to reduce the human labeling cost for
                 supervised learning methods. Determining when to stop
                 the active learning process is a very important
                 practical issue in real-world applications. This
                 article addresses the stopping criterion issue of
                 active learning, and presents four simple stopping
                 criteria based on confidence estimation over the
                 unlabeled data pool, including {\em maximum
                 uncertainty}, {\em overall uncertainty}, {\em selected
                 accuracy,\/} and {\em minimum expected error\/}
                 methods. Further, to obtain a proper threshold for a
                 stopping criterion in a specific task, this article
                 presents a strategy by considering the label change
                 factor to dynamically update the predefined threshold
                 of a stopping criterion during the active learning
                 process. To empirically analyze the effectiveness of
                 each stopping criterion for active learning, we design
                 several comparison experiments on seven real-world
                 datasets for three representative natural language
                 processing applications such as word sense
                 disambiguation, text classification and opinion
                 analysis.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "active learning; confidence estimation; stopping
                 criterion; text classification; uncertainty sampling;
                 word sense disambiguation",
}

@Article{Uzeda:2010:CCE,
  author =       "Vin{\'\i}cius Rodrigues Uz{\^e}da and Thiago Alexandre
                 Salgueiro Pardo and Maria Das Gra{\c{c}}as Volpe Nunes",
  title =        "A comprehensive comparative evaluation of {RST}-based
                 summarization methods",
  journal =      j-TSLP,
  volume =       "6",
  number =       "4",
  pages =        "4:1--4:??",
  month =        may,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1767756.1767757",
  ISSN =         "1550-4875",
  bibdate =      "Fri May 14 15:32:31 MDT 2010",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Motivated by governmental, commercial and academic
                 interests, and due to the growing amount of
                 information, mainly online, automatic text
                 summarization area has experienced an increasing number
                 of researches and products, which led to a countless
                 number of summarization methods. In this paper, we
                 present a comprehensive comparative evaluation of the
                 main automatic text summarization methods based on
                 Rhetorical Structure Theory (RST), claimed to be among
                 the best ones. We compare our results to superficial
                 summarizers, which belong to a paradigm with severe
                 limitations, and to hybrid methods, combining RST and
                 superficial methods. We also test voting systems and
                 machine learning techniques trained on RST features. We
                 run experiments for English and Brazilian Portuguese
                 languages and compare the results obtained by using
                 manually and automatically parsed texts. Our results
                 systematically show that all RST methods have
                 comparable overall performance and that they outperform
                 most of the superficial methods. Machine learning
                 techniques achieved high accuracy in the classification
                 of text segments worth of being in the summary, but
                 were not able to produce more informative summaries
                 than the regular RST methods.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "rhetorical structure theory; text summarization",
}

@Article{Morin:2010:BBU,
  author =       "Emmanuel Morin and B{\'e}atrice Daille and Koichi
                 Takeuchi and Kyo Kageura",
  title =        "Brains, not brawn: {The} use of ``smart'' comparable
                 corpora in bilingual terminology mining",
  journal =      j-TSLP,
  volume =       "7",
  number =       "1",
  pages =        "1:1--1:??",
  month =        aug,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1839478.1839479",
  ISSN =         "1550-4875",
  bibdate =      "Thu Sep 30 09:11:51 MDT 2010",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Current research in text mining favors the quantity of
                 texts over their representativeness. But for bilingual
                 terminology mining, and for many language pairs, large
                 comparable corpora are not available. More importantly,
                 as terms are defined vis-{\`a}-vis a specific domain
                 with a restricted register, it is expected that the
                 representativeness rather than the quantity of the
                 corpus matters more in terminology mining. Our
                 hypothesis, therefore, is that the representativeness
                 of the corpus is more important than the quantity and
                 ensures the quality of the acquired terminological
                 resources. This article tests this hypothesis on a
                 French--Japanese bilingual term extraction task. To
                 demonstrate how important the type of discourse is as a
                 characteristic of the comparable corpora, we used a
                 state-of-the-art multilingual terminology mining chain
                 composed of two extraction programs, one in each
                 language, and an alignment program. We evaluated the
                 candidate translations using a reference list, and
                 found that taking discourse type into account resulted
                 in candidate translations of a better quality even when
                 the corpus size was reduced by half.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
  keywords =     "comparable corpora; lexical alignment; Terminology
                 mining",
}

@Article{El-Beltagy:2011:AEL,
  author =       "Samhaa R. El-Beltagy and Ahmed Rafea",
  title =        "An accuracy-enhanced light stemmer for {Arabic} text",
  journal =      j-TSLP,
  volume =       "7",
  number =       "2",
  pages =        "2:1--2:??",
  month =        feb,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1921656.1921657",
  ISSN =         "1550-4875",
  bibdate =      "Tue Feb 22 16:47:19 MST 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Stemming is a key step in most text mining and
                 information retrieval applications. Information
                 extraction, semantic annotation, as well as ontology
                 learning are but a few examples where using a stemmer
                 is a must. While the use of light stemmers in Arabic
                 texts has proven highly effective for the task of
                 information retrieval, this class of stemmers falls
                 short of providing the accuracy required by many text
                 mining applications. This can be attributed to the fact
                 that light stemmers employ a set of rules that they
                 apply indiscriminately and that they do not address
                 stemming of broken plurals at all, even though this
                 class of plurals is very commonly used in Arabic
                 texts.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Lemon:2011:ISI,
  author =       "Oliver Lemon and Olivier Pietquin",
  title =        "Introduction to special issue on machine learning for
                 adaptivity in spoken dialogue systems",
  journal =      j-TSLP,
  volume =       "7",
  number =       "3",
  pages =        "3:1--3:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1966407.1966408",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jun 2 07:47:26 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Gavsic:2011:EHD,
  author =       "Milica Gav{\v{s}}i{\'c} and Steve Young",
  title =        "Effective handling of dialogue state in the hidden
                 information state {POMDP}-based dialogue manager",
  journal =      j-TSLP,
  volume =       "7",
  number =       "3",
  pages =        "4:1--4:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1966407.1966409",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jun 2 07:47:26 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Effective dialogue management is critically dependent
                 on the information that is encoded in the dialogue
                 state. In order to deploy reinforcement learning for
                 policy optimization, dialogue must be modeled as a
                 Markov Decision Process. This requires that the
                 dialogue state must encode all relevent information
                 obtained during the dialogue prior to that state. This
                 can be achieved by combining the user goal, the
                 dialogue history, and the last user action to form the
                 dialogue state. In addition, to gain robustness to
                 input errors, dialogue must be modeled as a Partially
                 Observable Markov Decision Process (POMDP) and hence, a
                 distribution over all possible states must be
                 maintained at every dialogue turn.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Cuayahuitl:2011:SAD,
  author =       "Heriberto Cuay{\'a}huitl and Nina Dethlefs",
  title =        "Spatially-aware dialogue control using hierarchical
                 reinforcement learning",
  journal =      j-TSLP,
  volume =       "7",
  number =       "3",
  pages =        "5:1--5:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1966407.1966410",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jun 2 07:47:26 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article addresses the problem of scalable
                 optimization for spatially-aware dialogue systems.
                 These kinds of systems must perceive, reason, and act
                 about the spatial environment where they are embedded.
                 We formulate the problem in terms of Semi-Markov
                 Decision Processes and propose a hierarchical
                 reinforcement learning approach to optimize
                 subbehaviors rather than full behaviors. Because of the
                 vast number of policies that are required to control
                 the interaction in a dynamic environment (e.g., a
                 dialogue system assisting a user to navigate in a
                 building from one location to another), our learning
                 approach is based on two stages: (a) the first stage
                 learns low-level behavior, in advance; and (b) the
                 second stage learns high-level behavior, in real
                 time.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Jurvcicek:2011:NAB,
  author =       "Filip Jurv{\v{c}}{\'\i}{\v{c}}ek and Blaise Thomson
                 and Steve Young",
  title =        "Natural actor and belief critic: Reinforcement
                 algorithm for learning parameters of dialogue systems
                 modelled as {POMDPs}",
  journal =      j-TSLP,
  volume =       "7",
  number =       "3",
  pages =        "6:1--6:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1966407.1966411",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jun 2 07:47:26 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article presents a novel algorithm for learning
                 parameters in statistical dialogue systems which are
                 modeled as Partially Observable Markov Decision
                 Processes (POMDPs). The three main components of a
                 POMDP dialogue manager are a dialogue model
                 representing dialogue state information; a policy that
                 selects the system's responses based on the inferred
                 state; and a reward function that specifies the desired
                 behavior of the system. Ideally both the model
                 parameters and the policy would be designed to maximize
                 the cumulative reward. However, while there are many
                 techniques available for learning the optimal policy,
                 no good ways of learning the optimal model parameters
                 that scale to real-world dialogue systems have been
                 found yet.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Pietquin:2011:SEB,
  author =       "Olivier Pietquin and Matthieu Geist and Senthilkumar
                 Chandramohan and Herv{\'e} Frezza-Buet",
  title =        "Sample-efficient batch reinforcement learning for
                 dialogue management optimization",
  journal =      j-TSLP,
  volume =       "7",
  number =       "3",
  pages =        "7:1--7:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1966407.1966412",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jun 2 07:47:26 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Spoken Dialogue Systems (SDS) are systems which have
                 the ability to interact with human beings using natural
                 language as the medium of interaction. A dialogue
                 policy plays a crucial role in determining the
                 functioning of the dialogue management module.
                 Handcrafting the dialogue policy is not always an
                 option, considering the complexity of the dialogue task
                 and the stochastic behavior of users. In recent years
                 approaches based on Reinforcement Learning (RL) for
                 policy optimization in dialogue management have been
                 proved to be an efficient approach for dialogue policy
                 optimization. Yet most of the conventional RL
                 algorithms are data intensive and demand techniques
                 such as user simulation.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Gonzalez-Brenes:2011:CDH,
  author =       "Jos{\'e} P. Gonz{\'a}lez-Brenes and Jack Mostow",
  title =        "Classifying dialogue in high-dimensional space",
  journal =      j-TSLP,
  volume =       "7",
  number =       "3",
  pages =        "8:1--8:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1966407.1966413",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jun 2 07:47:26 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "The richness of multimodal dialogue makes the space of
                 possible features required to describe it very large
                 relative to the amount of training data. However,
                 conventional classifier learners require large amounts
                 of data to avoid overfitting, or do not generalize well
                 to unseen examples. To learn dialogue classifiers using
                 a rich feature set and fewer data points than features,
                 we apply a recent technique, $\ell_1$-regularized
                 logistic regression. We demonstrate this approach
                 empirically on real data from Project LISTEN's Reading
                 Tutor, which displays a story on a computer screen and
                 listens to a child read aloud. We train a classifier to
                 predict task completion (i.e., whether the student will
                 finish reading the story) with 71\% accuracy on a
                 balanced, unseen test set.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Ai:2011:CUS,
  author =       "Hua Ai and Diane Litman",
  title =        "Comparing user simulations for dialogue strategy
                 learning",
  journal =      j-TSLP,
  volume =       "7",
  number =       "3",
  pages =        "9:1--9:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1966407.1966414",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jun 2 07:47:26 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Recent studies show that user simulations can be used
                 to generate training corpora for learning dialogue
                 strategies automatically. However, it is unclear what
                 type of simulation is most suitable in a particular
                 task setting. We observe that a simulation which
                 generates random behaviors in a restricted way
                 outperforms simulations that mimic human user behaviors
                 in a statistical way. Our finding suggests that we do
                 not always need to construct a realistic user
                 simulation. Since constructing realistic user
                 simulations is not a trivial task, we can save
                 engineering cost by wisely choosing simulation models
                 that are appropriate for our task.",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Misu:2011:MSD,
  author =       "Teruhisa Misu and Komei Sugiura and Tatsuya Kawahara
                 and Kiyonori Ohtake and Chiori Hori and Hideki Kashioka
                 and Hisashi Kawai and Satoshi Nakamura",
  title =        "Modeling spoken decision support dialogue and
                 optimization of its dialogue strategy",
  journal =      j-TSLP,
  volume =       "7",
  number =       "3",
  pages =        "10:1--10:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1966407.1966415",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jun 2 07:47:26 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article presents a user model for user simulation
                 and a system state representation in spoken decision
                 support dialogue systems. When selecting from a group
                 of alternatives, users apply different decision-making
                 criteria with different priorities. At the beginning of
                 the dialogue, however, users often do not have a
                 definite goal or criteria in which they place value,
                 thus they can learn about new features while
                 interacting with the system and accordingly create new
                 criteria. In this article, we present a user model and
                 dialogue state representation that accommodate these
                 patterns by considering the user's knowledge and
                 preferences. To estimate the parameters used in the
                 user model, we implemented a trial sightseeing guidance
                 system, collected dialogue data, and trained a user
                 simulator.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Potamianos:2011:ISI,
  author =       "Alexandros Potamianos and Diego Giuliani and Shrikanth
                 S. Narayanan and Kay Berkling",
  title =        "Introduction to the special issue on speech and
                 language processing of children's speech for
                 child-machine interaction applications",
  journal =      j-TSLP,
  volume =       "7",
  number =       "4",
  pages =        "11:1--11:??",
  month =        aug,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1998384.1998385",
  ISSN =         "1550-4875",
  bibdate =      "Wed Aug 17 09:52:06 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Wollmer:2011:TDC,
  author =       "Martin W{\"o}llmer and Bj{\"o}rn Schuller and Anton
                 Batliner and Stefan Steidl and Dino Seppi",
  title =        "Tandem decoding of children's speech for keyword
                 detection in a child-robot interaction scenario",
  journal =      j-TSLP,
  volume =       "7",
  number =       "4",
  pages =        "12:1--12:??",
  month =        aug,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1998384.1998386",
  ISSN =         "1550-4875",
  bibdate =      "Wed Aug 17 09:52:06 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "In this article, we focus on keyword detection in
                 children's speech as it is needed in voice command
                 systems. We use the FAU Aibo Emotion Corpus which
                 contains emotionally colored spontaneous children's
                 speech recorded in a child-robot interaction scenario
                 and investigate various recent keyword spotting
                 techniques. As the principle of bidirectional Long
                 Short-Term Memory (BLSTM) is known to be well-suited
                 for context-sensitive phoneme prediction, we
                 incorporate a BLSTM network into a Tandem model for
                 flexible coarticulation modeling in children's speech.
                 Our experiments reveal that the Tandem model prevails
                 over a triphone-based Hidden Markov Model approach.",
  acknowledgement = ack-nhfb,
  articleno =    "12",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Meinedo:2011:AGD,
  author =       "Hugo Meinedo and Isabel Trancoso",
  title =        "Age and gender detection in the {I-DASH} project",
  journal =      j-TSLP,
  volume =       "7",
  number =       "4",
  pages =        "13:1--13:??",
  month =        aug,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1998384.1998387",
  ISSN =         "1550-4875",
  bibdate =      "Wed Aug 17 09:52:06 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article presents a description of the INESC-ID
                 Age and Gender classification systems which were
                 developed for aiding the detection of child abuse
                 material within the scope of the European project
                 I-DASH. The Age and Gender classification systems are
                 composed respectively by the fusion of four and six
                 individual subsystems trained with short- and long-term
                 acoustic and prosodic features, different
                 classification strategies, Gaussian Mixture
                 Models-Universal Background Model (GMM-UBM),
                 Multi-Layer Perceptrons (MLP) and Support Vector
                 Machines (SVM), trained over five different speech
                 corpus. The best results obtained by the calibration
                 and linear logistic regression fusion back-end show an
                 absolute improvement of 2\% on the unweighted accuracy
                 value for the Age and 1\% for the Gender when compared
                 to the best individual frontend systems in the
                 development set.",
  acknowledgement = ack-nhfb,
  articleno =    "13",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Duong:2011:TMA,
  author =       "Minh Duong and Jack Mostow and Sunayana Sitaram",
  title =        "Two methods for assessing oral reading prosody",
  journal =      j-TSLP,
  volume =       "7",
  number =       "4",
  pages =        "14:1--14:??",
  month =        aug,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1998384.1998388",
  ISSN =         "1550-4875",
  bibdate =      "Wed Aug 17 09:52:06 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We compare two types of models to assess the prosody
                 of children's oral reading. Template models measure how
                 well the child's prosodic contour in reading a given
                 sentence correlates in pitch, intensity, pauses, or
                 word reading times with an adult narration of the same
                 sentence. We evaluate template models directly against
                 a common rubric used to assess fluency by hand, and
                 indirectly by their ability to predict fluency and
                 comprehension test scores and gains of 10 children who
                 used Project LISTEN's Reading Tutor; the template
                 models outpredict the human assessment. We also use the
                 same set of adult narrations to train generalized
                 models for mapping text to prosody, and use them to
                 evaluate children's prosody.",
  acknowledgement = ack-nhfb,
  articleno =    "14",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Black:2011:AAA,
  author =       "Matthew P. Black and Abe Kazemzadeh and Joseph
                 Tepperman and Shrikanth S. Narayanan",
  title =        "Automatically assessing the {ABCs}: Verification of
                 children's spoken letter-names and letter-sounds",
  journal =      j-TSLP,
  volume =       "7",
  number =       "4",
  pages =        "15:1--15:??",
  month =        aug,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1998384.1998389",
  ISSN =         "1550-4875",
  bibdate =      "Wed Aug 17 09:52:06 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Automatic literacy assessment is an area of research
                 that has shown significant progress in recent years.
                 Technology can be used to automatically administer
                 reading tasks and analyze and interpret children's
                 reading skills. It has the potential to transform the
                 classroom dynamic by providing useful information to
                 teachers in a repeatable, consistent, and affordable
                 way. While most previous research has focused on
                 automatically assessing children reading words and
                 sentences, assessments of children's earlier
                 foundational skills is needed. We address this problem
                 in this research by automatically verifying preliterate
                 children's pronunciations of English letter-names and
                 the sounds each letter represents (``letter-sounds'').
                 The children analyzed in this study were from a diverse
                 bilingual background and were recorded in actual
                 kindergarten to second grade classrooms.",
  acknowledgement = ack-nhfb,
  articleno =    "15",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Bolanos:2011:FFO,
  author =       "Daniel Bola{\~n}os and Ronald A. Cole and Wayne Ward
                 and Eric Borts and Edward Svirsky",
  title =        "{FLORA}: Fluent oral reading assessment of children's
                 speech",
  journal =      j-TSLP,
  volume =       "7",
  number =       "4",
  pages =        "16:1--16:??",
  month =        aug,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1998384.1998390",
  ISSN =         "1550-4875",
  bibdate =      "Wed Aug 17 09:52:06 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We present initial results of FLORA, an accessible
                 computer program that uses speech recognition to
                 provide an accurate measure of children's oral reading
                 ability. FLORA presents grade-level text passages to
                 children, who read the passages out loud, and computes
                 the number of words correct per minute (WCPM), a
                 standard measure of oral reading fluency. We describe
                 the main components of the FLORA program, including the
                 system architecture and the speech recognition
                 subsystems. We compare results of FLORA to human
                 scoring on 783 recordings of grade level text passages
                 read aloud by first through fourth grade students in
                 classroom settings.",
  acknowledgement = ack-nhfb,
  articleno =    "16",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Maier:2011:AVR,
  author =       "Andreas Maier and Flonan H{\"o}nig and Stefan Steidl
                 and Elmar N{\"o}th and Stefanie Horndasch and Elisabeth
                 Sauerh{\"o}fer and Oliver Kratz and Gunther Moll",
  title =        "An automatic version of a reading disorder test",
  journal =      j-TSLP,
  volume =       "7",
  number =       "4",
  pages =        "17:1--17:??",
  month =        aug,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1998384.1998391",
  ISSN =         "1550-4875",
  bibdate =      "Wed Aug 17 09:52:06 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We present a novel system to automatically diagnose
                 reading disorders. The system is based on a speech
                 recognition engine with a module for prosodic analysis.
                 The reading disorder test is based on eight different
                 subtests. In each of the subtests, the system achieves
                 a recognition accuracy of at least 95\%. As in the
                 perceptual version of the test, the results of the
                 subtests are then joined into a final test result to
                 determine whether the child has a reading disorder. In
                 the final classification stage, the system identifies
                 98.3\% of the 120 children correctly.",
  acknowledgement = ack-nhfb,
  articleno =    "17",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Ward:2011:MST,
  author =       "Wayne Ward and Ronald Cole and Daniel Bola{\~n}os and
                 Cindy Buchenroth-Martin and Edward Svirsky and Sarel
                 Van Vuuren and Timothy Weston and Jing Zheng and Lee
                 Becker",
  title =        "My science tutor: {A} conversational multimedia
                 virtual tutor for elementary school science",
  journal =      j-TSLP,
  volume =       "7",
  number =       "4",
  pages =        "18:1--18:??",
  month =        aug,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1998384.1998392",
  ISSN =         "1550-4875",
  bibdate =      "Wed Aug 17 09:52:06 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article describes My Science Tutor (MyST), an
                 intelligent tutoring system designed to improve science
                 learning by students in 3rd, 4th, and 5th grades (7 to
                 11 years old) through conversational dialogs with a
                 virtual science tutor. In our study, individual
                 students engage in spoken dialogs with the virtual
                 tutor Marni during 15 to 20 minute sessions following
                 classroom science investigations to discuss and extend
                 concepts embedded in the investigations. The spoken
                 dialogs in MyST are designed to scaffold learning by
                 presenting open-ended questions accompanied by
                 illustrations or animations related to the classroom
                 investigations and the science concepts being learned.
                 The focus of the interactions is to elicit
                 self-expression from students.",
  acknowledgement = ack-nhfb,
  articleno =    "18",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Turunen:2011:SRU,
  author =       "Ville T. Turunen and Mikko Kurimo",
  title =        "Speech retrieval from unsegmented {Finnish} audio
                 using statistical morpheme-like units for segmentation,
                 recognition, and retrieval",
  journal =      j-TSLP,
  volume =       "8",
  number =       "1",
  pages =        "1:1--1:??",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2036916.2036917",
  ISSN =         "1550-4875",
  bibdate =      "Thu Dec 15 08:44:09 MST 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Hassan:2011:LIE,
  author =       "Samer Hassan and Rada Mihalcea",
  title =        "Learning to identify educational materials",
  journal =      j-TSLP,
  volume =       "8",
  number =       "2",
  pages =        "2:1--2:??",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2050100.2050101",
  ISSN =         "1550-4875",
  bibdate =      "Thu Dec 15 08:44:09 MST 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Peirsman:2011:SRB,
  author =       "Yves Peirsman and Sebastian Pad{\'o}",
  title =        "Semantic relations in bilingual lexicons",
  journal =      j-TSLP,
  volume =       "8",
  number =       "2",
  pages =        "3:1--3:??",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2050100.2050102",
  ISSN =         "1550-4875",
  bibdate =      "Thu Dec 15 08:44:09 MST 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Kordjamshidi:2011:SRL,
  author =       "Parisa Kordjamshidi and Martijn {Van Otterlo} and
                 Marie-Francine Moens",
  title =        "Spatial role labeling: {Towards} extraction of spatial
                 relations from natural language",
  journal =      j-TSLP,
  volume =       "8",
  number =       "3",
  pages =        "4:1--4:??",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2050104.2050105",
  ISSN =         "1550-4875",
  bibdate =      "Thu Dec 15 08:44:09 MST 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article reports on the novel task of spatial role
                 labeling in natural language text. It proposes machine
                 learning methods to extract spatial roles and their
                 relations. This work experiments with both a step-wise
                 approach, where spatial prepositions are found and the
                 related trajectors, and landmarks are then extracted,
                 and a joint learning approach, where a spatial relation
                 and its composing indicator, trajector, and landmark
                 are classified collectively. Context-dependent learning
                 techniques, such as a skip-chain conditional random
                 field, yield good results on the GUM-evaluation
                 (Maptask) data and CLEF-IAPR TC-12 Image Benchmark.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Zhu:2012:UBA,
  author =       "Jingbo Zhu and Matthew Ma",
  title =        "Uncertainty-based active learning with instability
                 estimation for text classification",
  journal =      j-TSLP,
  volume =       "8",
  number =       "4",
  pages =        "5:1--5:??",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2093153.2093154",
  ISSN =         "1550-4875",
  bibdate =      "Wed Feb 15 18:13:35 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This article deals with pool-based active learning
                 with uncertainty sampling. While existing uncertainty
                 sampling methods emphasize selection of instances near
                 the decision boundary to increase the likelihood of
                 selecting informative examples, our position is that
                 this heuristic is a surrogate for selecting examples
                 for which the current learning algorithm iteration is
                 likely to misclassify. To more directly model this
                 intuition, this article augments such uncertainty
                 sampling methods and proposes a simple
                 instability-based selective sampling approach to
                 improving uncertainty-based active learning, in which
                 the instability degree of each unlabeled example is
                 estimated during the learning process. Experiments on
                 seven evaluation datasets show that instability-based
                 sampling methods can achieve significant improvements
                 over the traditional uncertainty sampling method.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Zhang:2012:ALS,
  author =       "Justin Jian Zhang and Pascale Fung",
  title =        "Active learning with semi-automatic annotation for
                 extractive speech summarization",
  journal =      j-TSLP,
  volume =       "8",
  number =       "4",
  pages =        "6:1--6:??",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2093153.2093155",
  ISSN =         "1550-4875",
  bibdate =      "Wed Feb 15 18:13:35 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We propose using active learning for extractive speech
                 summarization in order to reduce human effort in
                 generating reference summaries. Active learning chooses
                 a selective set of samples to be labeled. We propose a
                 combination of informativeness and representativeness
                 criteria for selection. We further propose a
                 semi-automatic method to generate reference summaries
                 for presentation speech by using Relaxed Dynamic Time
                 Warping (RDTW) alignment between presentation speech
                 and its accompanied slides. Our summarization results
                 show that the amount of labeled data needed for a given
                 summarization accuracy can be reduced by more than
                 23\% compared to random sampling.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Raux:2012:OTT,
  author =       "Antoine Raux and Maxine Eskenazi",
  title =        "Optimizing the turn-taking behavior of task-oriented
                 spoken dialog systems",
  journal =      j-TSLP,
  volume =       "9",
  number =       "1",
  pages =        "1:1--1:??",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2168748.2168749",
  ISSN =         "1550-4875",
  bibdate =      "Tue May 15 16:57:47 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Even as progress in speech technologies and task and
                 dialog modeling has allowed the development of advanced
                 spoken dialog systems, the low-level interaction
                 behavior of those systems often remains rigid and
                 inefficient. Based on an analysis of human-human and
                 human-computer turn-taking in naturally occurring
                 task-oriented dialogs, we define a set of features that
                 can be automatically extracted and show that they can
                 be used to inform efficient end-of-turn detection. We
                 then frame turn-taking as decision making under
                 uncertainty and describe the Finite-State Turn-Taking
                 Machine (FSTTM), a decision-theoretic model that
                 combines data-driven machine learning methods and a
                 cost structure derived from Conversation Analysis to
                 control the turn-taking behavior of dialog systems.
                 Evaluation results on CMU Let's Go, a publicly deployed
                 bus information system, confirm that the FSTTM
                 significantly improves the responsiveness of the system
                 compared to a standard threshold-based approach, as
                 well as previous data-driven methods.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Abdalgader:2012:USB,
  author =       "Khaled Abdalgader and Andrew Skabar",
  title =        "Unsupervised similarity-based word sense
                 disambiguation using context vectors and sentential
                 word importance",
  journal =      j-TSLP,
  volume =       "9",
  number =       "1",
  pages =        "2:1--2:??",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2168748.2168750",
  ISSN =         "1550-4875",
  bibdate =      "Tue May 15 16:57:47 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "The process of identifying the actual meanings of
                 words in a given text fragment has a long history in
                 the field of computational linguistics. Due to its
                 importance in understanding the semantics of natural
                 language, it is considered one of the most challenging
                 problems facing this field. In this article we propose
                 a new unsupervised similarity-based word sense
                 disambiguation (WSD) algorithm that operates by
                 computing the semantic similarity between glosses of
                 the target word and a context vector. The sense of the
                 target word is determined as that for which the
                 similarity between gloss and context vector is
                 greatest. Thus, whereas conventional unsupervised WSD
                 methods are based on measuring pairwise similarity
                 between words, our approach is based on measuring
                 semantic similarity between sentences. This enables it
                 to utilize a higher degree of semantic information, and
                 is more consistent with the way that human beings
                 disambiguate; that is, by considering the greater
                 context in which the word appears. We also show how
                 performance can be further improved by incorporating a
                 preliminary step in which the relative importance of
                 words within the original text fragment is estimated,
                 thereby providing an ordering that can be used to
                 determine the sequence in which words should be
                 disambiguated. We provide empirical results that show
                 that our method performs favorably against the
                 state-of-the-art unsupervised word sense disambiguation
                 methods, as evaluated on several benchmark datasets
                 through different models of evaluation.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Bouayad-Agha:2012:POG,
  author =       "Nadjet Bouayad-Agha and Gerard Casamayor and Simon
                 Mille and Leo Wanner",
  title =        "Perspective-oriented generation of football match
                 summaries: old tasks, new challenges",
  journal =      j-TSLP,
  volume =       "9",
  number =       "2",
  pages =        "3:1--3:??",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2287710.2287711",
  ISSN =         "1550-4875",
  bibdate =      "Tue Jul 31 17:49:24 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Team sports commentaries call for techniques that are
                 able to select content and generate wordings to reflect
                 the affinity of the targeted reader for one of the
                 teams. The existing works tend to have in common that
                 they either start from knowledge sources of limited
                 size to whose structures then different ways of
                 realization are explicitly assigned, or they work
                 directly with linguistic corpora, without the use of a
                 deep knowledge source. With the increasing availability
                 of large-scale ontologies this is no longer
                 satisfactory: techniques are needed that are applicable
                 to general purpose ontologies, but which still take
                 user preferences into account. We take the best of both
                 worlds in that we use a two-layer ontology. The first
                 layer is composed of raw domain data modelled in an
                 application-independent base OWL ontology. The second
                 layer contains a rich perspective generation-motivated
                 domain communication knowledge ontology, inferred from
                 the base ontology. The two-layer ontology allows us to
                 take into account user perspective-oriented criteria at
                 different stages of generation to generate
                 perspective-oriented commentaries. We show how content
                 selection, discourse structuring, information structure
                 determination, and lexicalization are driven by these
                 criteria and how stage after stage a truly user
                 perspective-tailored summary is generated. The
                 viability of our proposal has been evaluated for the
                 generation of football match summaries of the First
                 Spanish Football League. The reported outcome of the
                 evaluation demonstrates that we are on the right
                 track.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Sakti:2012:DST,
  author =       "Sakriani Sakti and Michael Paul and Andrew Finch and
                 Xinhui Hu and Jinfu Ni and Noriyuki Kimura and Shigeki
                 Matsuda and Chiori Hori and Yutaka Ashikari and Hisashi
                 Kawai and Hideki Kashioka and Eiichiro Sumita and
                 Satoshi Nakamura",
  title =        "Distributed speech translation technologies for
                 multiparty multilingual communication",
  journal =      j-TSLP,
  volume =       "9",
  number =       "2",
  pages =        "4:1--4:??",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2287710.2287712",
  ISSN =         "1550-4875",
  bibdate =      "Tue Jul 31 17:49:24 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Developing a multilingual speech translation system
                 requires efforts in constructing automatic speech
                 recognition (ASR), machine translation (MT), and
                 text-to-speech synthesis (TTS) components for all
                 possible source and target languages. If the numerous
                 ASR, MT, and TTS systems for different language pairs
                 developed independently in different parts of the world
                 could be connected, multilingual speech translation
                 systems for a multitude of language pairs could be
                 achieved. Yet, there is currently no common, flexible
                 framework that can provide an entire speech translation
                 process by bringing together heterogeneous speech
                 translation components. In this article we therefore
                 propose a distributed architecture framework for
                 multilingual speech translation in which all speech
                 translation components are provided on distributed
                 servers and cooperate over a network. This framework
                 can facilitate the connection of different components
                 and functions. To show the overall mechanism, we first
                 present our state-of-the-art technologies for
                 multilingual ASR, MT, and TTS components, and then
                 describe how to combine those systems into the proposed
                 network-based framework. The client applications are
                 implemented on a handheld mobile terminal device, and
                 all data exchanges among client users and spoken
                 language technology servers are managed through a Web
                 protocol. To support multiparty communication, an
                 additional communication server is provided for
                 simultaneously distributing the speech translation
                 results from one user to multiple users. Field testing
                 shows that the system is capable of realizing
                 multiparty multilingual speech translation for
                 real-time and location-independent communication.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Narendra:2012:SSU,
  author =       "N. P. Narendra and K. Sreenivasa Rao",
  title =        "Syllable Specific Unit Selection Cost Functions for
                 Text-to-Speech Synthesis",
  journal =      j-TSLP,
  volume =       "9",
  number =       "3",
  pages =        "5:1--5:??",
  month =        nov,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2382434.2382435",
  ISSN =         "1550-4875",
  bibdate =      "Tue Nov 20 18:42:07 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This paper presents the design and development of
                 syllable specific unit selection cost functions for
                 improving the quality of text-to-speech synthesis.
                 Appropriate unit selection cost functions, namely
                 concatenation cost and target cost, are proposed for
                 syllable based synthesis. Concatenation costs are
                 defined based on the type of segments present at the
                 syllable joins. Proposed concatenation costs have shown
                 significant reduction in perceptual discontinuity at
                 syllable joins. Three-stage target cost formulation is
                 proposed for selecting appropriate units from database.
                 Subjective evaluation has shown improvement in the
                 quality of speech at each stage.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Rentoumi:2012:IML,
  author =       "Vassiliki Rentoumi and George A. Vouros and Vangelis
                 Karkaletsis and Amalia Moser",
  title =        "Investigating Metaphorical Language in Sentiment
                 Analysis: a Sense-to-Sentiment Perspective",
  journal =      j-TSLP,
  volume =       "9",
  number =       "3",
  pages =        "6:1--6:??",
  month =        nov,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2382434.2382436",
  ISSN =         "1550-4875",
  bibdate =      "Tue Nov 20 18:42:07 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Intuition dictates that figurative language and
                 especially metaphorical expressions should convey
                 sentiment. It is the aim of this work to validate this
                 intuition by showing that figurative language
                 (metaphors) appearing in a sentence drive the polarity
                 of that sentence. Towards this target, the current
                 article proposes an approach for sentiment analysis of
                 sentences where figurative language plays a dominant
                 role. This approach applies Word Sense Disambiguation
                 aiming to assign polarity to word senses rather than
                 tokens. Sentence polarity is determined using the
                 individual polarities for metaphorical senses as well
                 as other contextual information. Experimental
                 evaluation shows that the proposed method achieves high
                 scores in comparison with other state-of-the-art
                 approaches tested on the same corpora. Finally,
                 experimental results provide supportive evidence that
                 this method is also well suited for corpora consisting
                 of literal and figurative language sentences.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Corazza:2013:ITM,
  author =       "Anna Corazza and Alberto Lavelli and Giorgio Satta",
  title =        "An information-theoretic measure to evaluate parsing
                 difficulty across treebanks",
  journal =      j-TSLP,
  volume =       "9",
  number =       "4",
  pages =        "7:1--7:??",
  month =        jan,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2407736.2407737",
  ISSN =         "1550-4875",
  bibdate =      "Wed Mar 20 06:19:16 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "With the growing interest in statistical parsing,
                 special attention has recently been devoted to the
                 problem of comparing different treebanks to assess
                 which languages or domains are more difficult to parse
                 relative to a given model. A common methodology for
                 comparing parsing difficulty across treebanks is based
                 on the use of the standard labeled precision and recall
                 measures. As an alternative, in this article we propose
                 an information-theoretic measure, called the expected
                 conditional cross-entropy (ECC). One important
                 advantage with respect to standard performance measures
                 is that ECC can be directly expressed as a function of
                 the parameters of the model. We evaluate ECC across
                 several treebanks for English, French, German, and
                 Italian, and show that ECC is an effective measure of
                 parsing difficulty, with an increase in ECC always
                 accompanied by a degradation in parsing accuracy.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Zhang:2013:CAL,
  author =       "Li Zhang",
  title =        "Contextual and active learning-based affect-sensing
                 from virtual drama improvisation",
  journal =      j-TSLP,
  volume =       "9",
  number =       "4",
  pages =        "8:1--8:??",
  month =        jan,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2407736.2407738",
  ISSN =         "1550-4875",
  bibdate =      "Wed Mar 20 06:19:16 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Affect interpretation from open-ended drama
                 improvisation is a challenging task. This article
                 describes experiments in using latent semantic analysis
                 to identify discussion themes and potential target
                 audiences for those improvisational inputs without
                 strong affect indicators. A context-based
                 affect-detection is also implemented using a supervised
                 neural network with the consideration of emotional
                 contexts of most intended audiences, sentence types,
                 and interpersonal relationships. In order to go beyond
                 the constraints of predefined scenarios and improve the
                 system's robustness, min-margin-based active learning
                 is implemented. This active learning algorithm also
                 shows great potential in dealing with imbalanced affect
                 classifications. Evaluation results indicated that the
                 context-based affect detection achieved an averaged
                 precision of 0.826 and an averaged recall of 0.813 for
                 affect detection of the test inputs from the Crohn's
                 disease scenario using three emotion labels: positive,
                 negative, and neutral, and an averaged precision of
                 0.868 and an average recall of 0.876 for the test
                 inputs from the school bullying scenario. Moreover,
                 experimental evaluation on a benchmark data set for
                 active learning demonstrated that active learning was
                 able to greatly reduce human annotation efforts for the
                 training of affect detection, and also showed promising
                 robustness in dealing with open-ended example inputs
                 beyond the improvisation of the chosen scenarios.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Duh:2013:MID,
  author =       "Kevin Duh and Ching-Man Au Yeung and Tomoharu Iwata
                 and Masaaki Nagata",
  title =        "Managing information disparity in multilingual
                 document collections",
  journal =      j-TSLP,
  volume =       "10",
  number =       "1",
  pages =        "1:1--1:??",
  month =        mar,
  year =         "2013",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Wed Mar 20 06:19:18 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Information disparity is a major challenge with
                 multilingual document collections. When documents are
                 dynamically updated in a distributed fashion,
                 information content among different language editions
                 may gradually diverge. We propose a framework for
                 assisting human editors to manage this information
                 disparity, using tools from machine translation and
                 machine learning. Given source and target documents in
                 two different languages, our system automatically
                 identifies information nuggets that are new with
                 respect to the target and suggests positions to place
                 their translations. We perform both real-world
                 experiments and large-scale simulations on Wikipedia
                 documents and conclude our system is effective in a
                 variety of scenarios.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Zhang:2013:TCL,
  author =       "Renxian Zhang and Wenjie Li and Dehong Gao",
  title =        "Towards content-level coherence with aspect-guided
                 summarization",
  journal =      j-TSLP,
  volume =       "10",
  number =       "1",
  pages =        "2:1--2:??",
  month =        mar,
  year =         "2013",
  CODEN =        "????",
  ISSN =         "1550-4875",
  bibdate =      "Wed Mar 20 06:19:18 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "The TAC 2010 summarization track initiated a new
                 task-aspect-guided summarization-that centers on
                 textual aspects embodied as particular kinds of
                 information of a text. We observe that aspect-guided
                 summaries not only address highly specific user need,
                 but also facilitate content-level coherence by using
                 aspect information. In this article, we present a
                 full-fledged approach to aspect-guided summarization
                 with a focus on summary coherence. Our summarization
                 approach depends on two prerequisite subtasks:
                 recognizing aspect-bearing sentences in order to do
                 sentence extraction, and modeling aspect-based
                 coherence with an HMM model in order to predict a
                 coherent sentence ordering. Using the manually
                 annotated TAC 2010 and 2010 datasets, we validated the
                 effectiveness of our proposed methods for those
                 subtasks. Drawing on the empirical results, we proceed
                 to develop an aspect-guided summarizer based on a
                 simple but robust base summarizer. With sentence
                 selection guided by aspect information, our system is
                 one of the best on TAC 2011. With sentence ordering
                 predicted by the aspect-based HMM model, the summaries
                 achieve good coherence.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Ramisch:2013:ISI,
  author =       "Carlos Ramisch and Aline Villavicencio and Valia
                 Kordoni",
  title =        "Introduction to the special issue on multiword
                 expressions: From theory to practice and use",
  journal =      j-TSLP,
  volume =       "10",
  number =       "2",
  pages =        "3:1--3:??",
  month =        jun,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483691.2483692",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 1 18:16:29 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We are in 2013, and multiword expressions have been
                 around for a while in the computational linguistics
                 research community. Since the first ACL workshop on
                 MWEs 12 years ago in Sapporo, Japan, much has been
                 discussed, proposed, experimented, evaluated and argued
                 about MWEs. And yet, they deserve the publication of a
                 whole special issue of the ACM Transactions on Speech
                 and Language Processing. But what is it about multiword
                 expressions that keeps them in fashion? Who are the
                 people and the institutions who perform and publish
                 groundbreaking fundamental and applied research in this
                 field? What is the place and the relevance of our
                 lively research community in the bigger picture of
                 computational linguistics? Where do we come from as a
                 community, and most importantly, where are we heading?
                 In this introductory article, we share our point of
                 view about the answers to these questions and introduce
                 the articles that compose the current special issue.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Church:2013:HMM,
  author =       "Kenneth Church",
  title =        "How many multiword expressions do people know?",
  journal =      j-TSLP,
  volume =       "10",
  number =       "2",
  pages =        "4:1--4:??",
  month =        jun,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483691.2483693",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 1 18:16:29 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "What is a multiword expression (MWE) and how many are
                 there? Mark Liberman gave a great invited talk at
                 ACL-89, titled ``How Many Words Do People Know?'' where
                 he spent the entire hour questioning the question. Many
                 of the same questions apply to multiword expressions.
                 What is a word? An expression? What is many? What is a
                 person? What does it mean to know? Rather than answer
                 these questions, this article will use them as Liberman
                 did, as an excuse for surveying how such issues are
                 addressed in a variety of fields: computer science, Web
                 search, linguistics, lexicography, educational testing,
                 psychology, statistics, and so on.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Davis:2013:LSF,
  author =       "Anthony R. Davis and Leslie Barrett",
  title =        "Lexical semantic factors in the acceptability of
                 {English} support-verb-nominalization constructions",
  journal =      j-TSLP,
  volume =       "10",
  number =       "2",
  pages =        "5:1--5:??",
  month =        jun,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483691.2483694",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 1 18:16:29 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We explore the properties of support-verb and
                 nominalization (SVN) pairs in English, a type of
                 multiword expression in which a semantically
                 impoverished verb combines with a complement
                 nominalization sharing an unexpressed role with the
                 verb. This study follows others in seeking syntactic or
                 lexical semantic factors correlated with the
                 acceptability of these constructions. In particular,
                 following recent work showing certain semantic verb
                 class features to improve SVN classification [Tu and
                 Roth 2011], we explore the possibility that support
                 verbs and the verbal roots of nominalizations in
                 acceptable SVN pairs are clustered according to the
                 classes of Levin [1993]. We compare the compatibility
                 correlation of these results with those of the
                 Aktionsart-class-based proposal of Barrett and Davis
                 [2002]. We find the evidence that Levin classes are a
                 factor in the acceptability of SVN constructions to be
                 equivocal, and conclude with a discussion of the
                 reasons for this finding.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Vincze:2013:LDE,
  author =       "Veronika Vincze and Istv{\'a}n Nagy T. and J{\'a}nos
                 Zsibrita",
  title =        "Learning to detect {English} and {Hungarian} light
                 verb constructions",
  journal =      j-TSLP,
  volume =       "10",
  number =       "2",
  pages =        "6:1--6:??",
  month =        jun,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483691.2483695",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 1 18:16:29 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Light verb constructions consist of a verbal and a
                 nominal component, where the noun preserves its
                 original meaning while the verb has lost it (to some
                 degree). They are syntactically flexible and their
                 meaning can only be partially computed on the basis of
                 the meaning of their parts, thus they require special
                 treatment in natural language processing. For this
                 purpose, the first step is to identify light verb
                 constructions. In this study, we present our
                 conditional random fields-based tool-called
                 FXTagger-for identifying light verb constructions. The
                 flexibility of the tool is demonstrated on two,
                 typologically different, languages, namely, English and
                 Hungarian. As earlier studies labeled different
                 linguistic phenomena as light verb constructions, we
                 first present a linguistics-based classification of
                 light verb constructions and then show that FXTagger is
                 able to identify different classes of light verb
                 constructions in both languages. Different types of
                 texts may contain different types of light verb
                 constructions; moreover, the frequency of light verb
                 constructions may differ from domain to domain. Hence
                 we focus on the portability of models trained on
                 different corpora, and we also investigate the effect
                 of simple domain adaptation techniques to reduce the
                 gap between the domains. Our results show that in spite
                 of domain specificities, out-domain data can also
                 contribute to the successful LVC detection in all
                 domains.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Nissim:2013:MIV,
  author =       "Malvina Nissim and Andrea Zaninello",
  title =        "Modeling the internal variability of multiword
                 expressions through a pattern-based method",
  journal =      j-TSLP,
  volume =       "10",
  number =       "2",
  pages =        "7:1--7:??",
  month =        jun,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483691.2483696",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 1 18:16:29 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "The issue of internal variability of multiword
                 expressions (MWEs) is crucial towards their
                 identification and extraction in running text. We
                 present a corpus-supported and computational study on
                 Italian MWEs, aimed at defining an automatic method for
                 modeling internal variation, exploiting frequency and
                 part-of-speech (POS) information. We do so by deriving
                 an XML-encoded lexicon of MWEs based on a manually
                 compiled dictionary, which is then projected onto a a
                 large corpus. Since a search for fixed forms suffers
                 from low recall, while an unconstrained flexible search
                 for lemmas yields a loss in precision, we suggest a
                 procedure aimed at maximizing precision in the
                 identification of MWEs within a flexible search. Our
                 method builds on the idea that internal variability can
                 be modelled via the novel introduction of variation
                 patterns, which work over POS patterns, and can be used
                 as working tools for controlling precision. We also
                 compare the performance of variation patterns to that
                 of association measures, and explore the possibility of
                 using variation patterns in MWE extraction in addition
                 to identification. Finally, we suggest that
                 corpus-derived, pattern-related information can be
                 included in the original MWE lexicon by means of an
                 enriched coding and the creation of an XML-based
                 repository of patterns.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Anonymous:2013:R,
  author =       "Anonymous",
  title =        "Reviewers",
  journal =      j-TSLP,
  volume =       "10",
  number =       "2",
  pages =        "8:1--8:??",
  month =        jun,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483691.2499382",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 1 18:16:29 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Constant:2013:CCR,
  author =       "Matthieu Constant and Joseph {Le Roux} and Anthony
                 Sigogne",
  title =        "Combining compound recognition and {PCFG--LA} parsing
                 with word lattices and conditional random fields",
  journal =      j-TSLP,
  volume =       "10",
  number =       "3",
  pages =        "8:1--8:??",
  month =        jul,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483969.2483970",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 8 17:25:06 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "The integration of compounds in a parsing procedure
                 has been shown to improve accuracy in an artificial
                 context where such expressions have been perfectly
                 preidentified. This article evaluates two empirical
                 strategies to incorporate such multiword units in a
                 real PCFG-LA parsing context: (1) the use of a grammar
                 including compound recognition, thanks to specialized
                 annotation schemes for compounds; (2) the use of a
                 state-of-the-art discriminative compound prerecognizer
                 integrating endogenous and exogenous features. We show
                 how these two strategies can be combined with word
                 lattices representing possible lexical analyses
                 generated by the recognizer. The proposed systems
                 display significant gains in terms of multiword
                 recognition and often in terms of standard parsing
                 accuracy. Moreover, we show through an Oracle analysis
                 that this combined strategy opens promising new
                 research directions.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Kim:2013:WSS,
  author =       "Su Nam Kim and Timothy Baldwin",
  title =        "Word sense and semantic relations in noun compounds",
  journal =      j-TSLP,
  volume =       "10",
  number =       "3",
  pages =        "9:1--9:??",
  month =        jul,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483969.2483971",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 8 17:25:06 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "In this article, we investigate word sense
                 distributions in noun compounds (NCs). Our primary goal
                 is to disambiguate the word sense of component words in
                 NCs, based on investigation of ``semantic collocation''
                 between them. We use sense collocation and lexical
                 substitution to build supervised and unsupervised word
                 sense disambiguation (WSD) classifiers, and show our
                 unsupervised learner to be superior to a benchmark WSD
                 system. Further, we develop a word sense-based approach
                 to interpreting the semantic relations in NCs.",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Lau:2013:CTM,
  author =       "Jey Han Lau and Timothy Baldwin and David Newman",
  title =        "On collocations and topic models",
  journal =      j-TSLP,
  volume =       "10",
  number =       "3",
  pages =        "10:1--10:??",
  month =        jul,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483969.2483972",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 8 17:25:06 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We investigate the impact of preextracting and
                 tokenizing bigram collocations on topic models. Using
                 extensive experiments on four different corpora, we
                 show that incorporating bigram collocations in the
                 document representation creates more parsimonious
                 models and improves topic coherence. We point out some
                 problems in interpreting test likelihood and test
                 perplexity to compare model fit, and suggest an
                 alternate measure that penalizes model complexity. We
                 show how the Akaike information criterion is a more
                 appropriate measure, which suggests that using a modest
                 number (up to 1000) of top-ranked bigrams is the
                 optimal topic modelling configuration. Using these 1000
                 bigrams also results in improved topic quality over
                 unigram tokenization. Further increases in topic
                 quality can be achieved by using up to 10,000 bigrams,
                 but this is at the cost of a more complex model. We
                 also show that multiword (bigram and longer) named
                 entities give consistent results, indicating that they
                 should be represented as single tokens. This is the
                 first work to explicitly study the effect of n -gram
                 tokenization on LDA topic models, and the first work to
                 make empirical recommendations to topic modelling
                 practitioners, challenging the standard practice of
                 unigram-based tokenization.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Shutova:2013:CML,
  author =       "Ekaterina Shutova and Jakub Kaplan and Simone Teufel
                 and Anna Korhonen",
  title =        "A computational model of logical metonymy",
  journal =      j-TSLP,
  volume =       "10",
  number =       "3",
  pages =        "11:1--11:??",
  month =        jul,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483969.2483973",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 8 17:25:06 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "The use of figurative language is ubiquitous in
                 natural language texts and it is a serious bottleneck
                 in automatic text understanding. A system capable of
                 interpreting figurative expressions would be an
                 invaluable addition to the real-world natural language
                 processing (NLP) applications that need to access
                 semantics, such as machine translation, opinion mining,
                 question answering and many others. In this article we
                 focus on one type of figurative language, logical
                 metonymy, and present a computational model of its
                 interpretation bringing together statistical techniques
                 and the insights from linguistic theory. Compared to
                 previous approaches this model is both more informative
                 and more accurate. The system produces sense-level
                 interpretations of metonymic phrases and then
                 automatically organizes them into conceptual classes,
                 or roles, discussed in the majority of linguistic
                 literature on the phenomenon.",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Klebanov:2013:SPM,
  author =       "Beata Beigman Klebanov and Jill Burstein and Nitin
                 Madnani",
  title =        "Sentiment profiles of multiword expressions in
                 test-taker essays: The case of noun--noun compounds",
  journal =      j-TSLP,
  volume =       "10",
  number =       "3",
  pages =        "12:1--12:??",
  month =        jul,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483969.2483974",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 8 17:25:06 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "The property of idiomaticity vs. compositionality of a
                 multiword expression traditionally pertains to the
                 semantic interpretation of the expression. In this
                 article, we consider this property as it applies to the
                 expression's sentiment profile (relative degree of
                 positivity, negativity, and neutrality). Thus, while
                 heart attack is idiomatic in terms of semantic
                 interpretation, the sentiment profile of the expression
                 (strongly negative) can, in fact, be determined from
                 the strongly negative profile of the head word. In this
                 article, we (1) propose a way to measure
                 compositionality of a multiword expression's sentiment
                 profile, and perform the measurement on noun-noun
                 compounds; (2) evaluate the utility of using sentiment
                 profiles of noun-noun compounds in a sentence-level
                 sentiment classification task. We find that the
                 sentiment profiles of noun-noun compounds in test-taker
                 essays tend to be highly compositional and that their
                 incorporation improves the performance of a sentiment
                 classification system.",
  acknowledgement = ack-nhfb,
  articleno =    "12",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Nakov:2013:SIN,
  author =       "Preslav I. Nakov and Marti A. Hearst",
  title =        "Semantic interpretation of noun compounds using verbal
                 and other paraphrases",
  journal =      j-TSLP,
  volume =       "10",
  number =       "3",
  pages =        "13:1--13:??",
  month =        jul,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2483969.2483975",
  ISSN =         "1550-4875",
  bibdate =      "Mon Jul 8 17:25:06 MDT 2013",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "We study the problem of semantic interpretation of
                 noun compounds such as bee honey, malaria mosquito,
                 apple cake, and stem cell. In particular, we explore
                 the potential of using predicates that make explicit
                 the hidden relation that holds between the nouns that
                 form the noun compound. For example, mosquito that
                 carries malaria is a paraphrase of the compound malaria
                 mosquito in which the verb explicitly states the
                 semantic relation between the two nouns. We study the
                 utility of using such paraphrasing verbs, with
                 associated weights, to build a representation of the
                 semantics of a noun compound, for example, malaria
                 mosquito can be represented as follows: carry (23),
                 spread (16), cause (12), transmit (9), and so on. We
                 also explore the potential of using multiple
                 paraphrasing verbs as features for predicting abstract
                 semantic relations such as CAUSE, and we demonstrate
                 that using explicit paraphrases can help improve
                 statistical machine translation.",
  acknowledgement = ack-nhfb,
  articleno =    "13",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Editors:2013:E,
  author =       "{The Editors}",
  title =        "Editorial",
  journal =      j-TSLP,
  volume =       "10",
  number =       "4",
  pages =        "14:1--14:??",
  month =        dec,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2556529",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jan 9 10:56:30 MST 2014",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  acknowledgement = ack-nhfb,
  articleno =    "14",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Meguro:2013:LCL,
  author =       "Toyomi Meguro and Yasuhiro Minami and Ryuichiro
                 Higashinaka and Kohji Dohsaka",
  title =        "Learning to control listening-oriented dialogue using
                 partially observable {Markov} decision processes",
  journal =      j-TSLP,
  volume =       "10",
  number =       "4",
  pages =        "15:1--15:??",
  month =        dec,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2513145",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jan 9 10:56:30 MST 2014",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Our aim is to build listening agents that attentively
                 listen to their users and satisfy their desire to speak
                 and have themselves heard. This article investigates
                 how to automatically create a dialogue control
                 component of such a listening agent. We collected a
                 large number of listening-oriented dialogues with their
                 user satisfaction ratings and used them to create a
                 dialogue control component that satisfies users by
                 means of Partially Observable Markov Decision Processes
                 (POMDPs). Using a hybrid dialog controller where
                 high-level dialog acts are chosen with a statistical
                 policy and low-level slot values are populated by a
                 wizard, we evaluated our dialogue control method in a
                 Wizard-of-Oz experiment. The experimental results show
                 that our POMDP-based method achieves significantly
                 higher user satisfaction than other stochastic models,
                 confirming the validity of our approach. This article
                 is the first to verify, by using human users, the
                 usefulness of POMDP-based dialogue control for
                 improving user satisfaction in nontask-oriented
                 dialogue systems.",
  acknowledgement = ack-nhfb,
  articleno =    "15",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Cai:2013:CCC,
  author =       "Xiaoyan Cai and Wenjie Li and Renxian Zhang",
  title =        "Combining co-clustering with noise detection for
                 theme-based summarization",
  journal =      j-TSLP,
  volume =       "10",
  number =       "4",
  pages =        "16:1--16:??",
  month =        dec,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2513563",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jan 9 10:56:30 MST 2014",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "To overcome the fact that the length of sentences is
                 short and their content is limited, we regard words as
                 independent text objects rather than features of
                 sentences in sentence clustering and develop two
                 co-clustering frameworks, namely integrated clustering
                 and interactive clustering, to cluster sentences and
                 words simultaneously. Since real-world datasets always
                 contain noise, we incorporate noise detection and
                 removal to enhance clustering of sentences and words.
                 Meanwhile, a semisupervised approach is explored to
                 incorporate the query information (and the sentence
                 information in early document sets) in theme-based
                 summarization. Thorough experimental studies are
                 conducted. When evaluated on the DUC2005-2007 datasets
                 and TAC 2008-2009 datasets, the performance of the two
                 noise-detecting co-clustering approaches is comparable
                 with that of the top three systems. The results also
                 demonstrate that the interactive with noise detection
                 algorithm is more effective than the noise-detecting
                 integrated algorithm.",
  acknowledgement = ack-nhfb,
  articleno =    "16",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Blanco:2013:CSR,
  author =       "Eduardo Blanco and Dan Moldovan",
  title =        "Composition of semantic relations: Theoretical
                 framework and case study",
  journal =      j-TSLP,
  volume =       "10",
  number =       "4",
  pages =        "17:1--17:??",
  month =        dec,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2513146",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jan 9 10:56:30 MST 2014",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Extracting semantic relations from text is a
                 preliminary step towards understanding the meaning of
                 text. The more semantic relations are extracted from a
                 sentence, the better the representation of the
                 knowledge encoded into that sentence. This article
                 introduces a framework for the Composition of Semantic
                 Relations (CSR). CSR aims to reveal more text semantics
                 than existing semantic parsers by composing new
                 relations out of previously extracted relations.
                 Semantic relations are defined using vectors of
                 semantic primitives, and an algebra is suggested to
                 manipulate these vectors according to a CSR algorithm.
                 Inference axioms that combine two relations and yield
                 another relation are generated automatically. CSR is a
                 language-agnostic, inventory-independent method to
                 extract semantic relations. The formalism has been
                 applied to a set of 26 well-known relations and results
                 are reported.",
  acknowledgement = ack-nhfb,
  articleno =    "17",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Sokolov:2013:LBO,
  author =       "Artem Sokolov and Guillaume Wisniewski and
                 Fran{\c{c}}ois Yvon",
  title =        "Lattice {BLEU} oracles in machine translation",
  journal =      j-TSLP,
  volume =       "10",
  number =       "4",
  pages =        "18:1--18:??",
  month =        dec,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2513147",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jan 9 10:56:30 MST 2014",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "The search space of Phrase-Based Statistical Machine
                 Translation (PBSMT) systems can be represented as a
                 directed acyclic graph (lattice). By exploring this
                 search space, it is possible to analyze and understand
                 the failures of PBSMT systems. Indeed, useful diagnoses
                 can be obtained by computing the so-called oracle
                 hypotheses, which are hypotheses in the search space
                 that have the highest quality score. For standard SMT
                 metrics, this problem is, however, NP-hard and can only
                 be solved approximately. In this work, we present two
                 new methods for efficiently computing oracles on
                 lattices: the first one is based on a linear
                 approximation of the corpus bleu score and is solved
                 using generic shortest distance algorithms; the second
                 one relies on an Integer Linear Programming (ILP)
                 formulation of the oracle decoding that incorporates
                 count clipping constraints. It can either be solved
                 directly using a standard ILP solver or using
                 Lagrangian relaxation techniques. These new decoders
                 are evaluated and compared with several alternatives
                 from the literature for three language pairs, using
                 lattices produced by two PBSMT systems.",
  acknowledgement = ack-nhfb,
  articleno =    "18",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Oshea:2013:NBD,
  author =       "James O'shea and Zuhair Bandar and Keeley Crockett",
  title =        "A new benchmark dataset with production methodology
                 for short text semantic similarity algorithms",
  journal =      j-TSLP,
  volume =       "10",
  number =       "4",
  pages =        "19:1--19:??",
  month =        dec,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2537046",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jan 9 10:56:30 MST 2014",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "This research presents a new benchmark dataset for
                 evaluating Short Text Semantic Similarity (STSS)
                 measurement algorithms and the methodology used for its
                 creation. The power of the dataset is evaluated by
                 using it to compare two established algorithms, STASIS
                 and Latent Semantic Analysis. This dataset focuses on
                 measures for use in Conversational Agents; other
                 potential applications include email processing and
                 data mining of social networks. Such applications
                 involve integrating the STSS algorithm in a complex
                 system, but STSS algorithms must be evaluated in their
                 own right and compared with others for their
                 effectiveness before systems integration. Semantic
                 similarity is an artifact of human perception;
                 therefore its evaluation is inherently empirical and
                 requires benchmark datasets derived from human
                 similarity ratings. The new dataset of 64 sentence
                 pairs, STSS-131, has been designed to meet these
                 requirements drawing on a range of resources from
                 traditional grammar to cognitive neuroscience. The
                 human ratings are obtained from a set of trials using
                 new and improved experimental methods, with validated
                 measures and statistics. The results illustrate the
                 increased challenge and the potential longevity of the
                 STSS-131 dataset as the Gold Standard for future STSS
                 algorithm evaluation.",
  acknowledgement = ack-nhfb,
  articleno =    "19",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}

@Article{Roy:2013:CCN,
  author =       "Suman Deb Roy and Wenjun Zeng",
  title =        "Cognitive canonicalization of natural language queries
                 using semantic strata",
  journal =      j-TSLP,
  volume =       "10",
  number =       "4",
  pages =        "20:1--20:??",
  month =        dec,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2539053",
  ISSN =         "1550-4875",
  bibdate =      "Thu Jan 9 10:56:30 MST 2014",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/tslp.bib",
  abstract =     "Natural language search relies strongly on perceiving
                 semantics in a query sentence. Semantics is captured by
                 the relationship among the query words, represented as
                 a network (graph). Such a network of words can be fed
                 into larger ontologies, like DBpedia or Google
                 Knowledge Graph, where they appear as subgraphs-
                 fashioning the name subnetworks (subnets). Thus, subnet
                 is a canonical form for interfacing a natural language
                 query to a graph database and is an integral step for
                 graph-based searching. In this article, we present a
                 novel standalone NLP technique that leverages the
                 cognitive psychology notion of semantic strata for
                 semantic subnetwork extraction from natural language
                 queries. The cognitive model describes some of the
                 fundamental structures employed by the human cognition
                 to construct semantic information in the brain, called
                 semantic strata. We propose a computational model based
                 on conditional random fields to capture the cognitive
                 abstraction provided by semantic strata, facilitating
                 cognitive canonicalization of the query. Our results,
                 conducted on approximately 5000 queries, suggest that
                 the cognitive canonicals based on semantic strata are
                 capable of significantly improving parsing and role
                 labeling performance beyond pure lexical approaches,
                 such as parts-of-speech based techniques. We also find
                 that cognitive canonicalized subnets are more
                 semantically coherent compared to syntax trees when
                 explored in graph ontologies like DBpedia and improve
                 ranking of retrieved documents.",
  acknowledgement = ack-nhfb,
  articleno =    "20",
  fjournal =     "ACM Transactions on Speech and Language Processing
                 (TSLP)",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J957",
}