input.bib

@INPROCEEDINGS{Altun:2003:EMNLP,
  AUTHOR = {Altun, Yasemin  and  Johnson, Mark  and  Hofmann, Thomas},
  TITLE = {Investigating Loss Functions and Optimization Methods for Discriminative Learning of Label Sequences},
  BOOKTITLE = {Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing},
  EDITOR = {Michael Collins and Mark Steedman},
  URL = {http://www.aclweb.org/anthology/W03-1019.pdf},
  YEAR = 2003,
  PAGES = {145--152}
}

@INPROCEEDINGS{Altun:2003:EuroSpeech,
  TITLE = {Large Margin Methods for Label Sequence Learning},
  BOOKTITLE = {Proceedings of the Eighth European Conference on Speech Communication and Technology (EuroSpeech'03)},
  AUTHOR = {Yasemin Altun and Thomas Hofmann},
  YEAR = {2003},
  ABSTRACT = {Label sequence learning is the problem of inferring a
		 state sequence from an observation sequence, where the
		 state sequence may encode a labeling, annotation or
		 segmentation of the sequence. In this paper we give an
		 overview of discriminative methods developed for this
		 problem. Special emphasis is put on large margin
		 methods by generalizing multiclass Support Vector
		 Machines and AdaBoost to the case of label sequences.
		 An experimental evaluation demonstrates the advantages
		 over classical approaches like Hidden Markov Models and
		 the competitiveness with methods like Conditional
		 Random Fields.},
  PDF = {http://ttic.uchicago.edu/~altun/pubs/AltunHofmann-EuroSpeech2003.pdf}
}

@INPROCEEDINGS{altunhofmj02,
  AUTHOR = {Yasemin Altun and Thomas Hofmann and Mark Johnson},
  TITLE = {Discriminative Learning for Label Sequences via Boosting},
  BOOKTITLE = {Proceedings of Neural Information Processing Systems (NIPS02)},
  YEAR = {2002},
  URL = {http://books.nips.cc/papers/files/nips15/AA63.pdf}
}

@INPROCEEDINGS{Altun01,
  AUTHOR = {Altun, Yasemin and Johnson, Mark},
  TITLE = {Inducing SFA with Epsilon-Translations Using Minimum Description Length},
  BOOKTITLE = {Finite State Methods in Natural Language Processing Workshop, ESSLLI 2001},
  YEAR = 2001,
  URL = {http://ttic.uchicago.edu/~altun/pubs/AltJohn_ESSLLI2001.pdf}
}

@INPROCEEDINGS{bayermj95,
  AUTHOR = {Sam Bayer and Mark Johnson},
  TITLE = {Features and Agreement},
  BOOKTITLE = {Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics (ACL-95)},
  YEAR = {1995},
  PAGES = {70-76},
  URL = {http://arxiv.org/pdf/cmp-lg/9506007},
  ABSTRACT = {This paper compares the consistency-based account of agreement phenomena in `unification-based' grammars with an implication-based account based on a simple feature extension to Lambek Categorial Grammar (LCG). We show that the LCG treatment accounts for constructions that have been recognized as problematic for `unification-based' treatments.}
}

@INPROCEEDINGS{Berland-Charniak:ACL:99,
  AUTHOR = {Matthew Berland and Eugene Charniak},
  TITLE = {Finding parts in very large corpora},
  BOOKTITLE = {Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (ACL '99)},
  YEAR = {1999},
  PAGES = {57--64},
  URL = {http://acl.ldc.upenn.edu/P/P99/P99-1008.pdf},
  TECHREPORT = {ftp://ftp.cs.brown.edu/pub/techreports/99/cs99-02.ps.Z}
}

@INPROCEEDINGS{Bies06,
  AUTHOR = {Ann Bies and Stephanie Strassel and Haejoong Lee and Kazuaki Maeda and Seth Kulick and Yang Liu and Mary Harper and Matthew Lease},
  TITLE = {Linguistic Resources for Speech Parsing},
  BOOKTITLE = {Fifth International Conference on Language Resources and Evaluation (LREC'06)},
  YEAR = 2006,
  ADDRESS = {Genoa, Italy},
  PDF = {http://papers.ldc.upenn.edu/LREC2006/LinguisticResourcesForSpeechParsing.pdf}
}

@INPROCEEDINGS{blaheta:2002:EMNLP,
  AUTHOR = {Don Blaheta},
  TITLE = {Handling noisy training and testing data},
  BOOKTITLE = {Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing},
  YEAR = {2002},
  MONTH = {July},
  ADDRESS = {Philadelpha, Pennsylvania},
  URL = {http://acl.ldc.upenn.edu/acl2002/EMNLP/pdfs/EMNLP207.pdf}
}

@INPROCEEDINGS{blaheta-johnson:2001:ACL,
  AUTHOR = {Blaheta, Don and Johnson, Mark},
  TITLE = {Unsupervised learning of multi-word verbs},
  BOOKTITLE = {Proceedings of the 2001 ACL Workshop on Collocation},
  YEAR = {2001},
  URL = {http://www.cog.brown.edu/%7Emj/papers/2001/dpb-colloc01.pdf}
}

@INPROCEEDINGS{Blaheta-Charniak:NAACL:2000,
  AUTHOR = {Don Blaheta and Eugene Charniak},
  TITLE = {Assigning function tags to parsed text},
  BOOKTITLE = {Proceedings of the First Conference of the North American chapter of the Association for Computational Linguistics (NAACL '00)},
  YEAR = {2000},
  PAGES = {234--240},
  LOCATION = {Seattle, Washington},
  URL = {http://acl.ldc.upenn.edu/A/A00/A00-2031.pdf}
}

@INPROCEEDINGS{blaheta99-acl,
  AUTHOR = {Don Blaheta and Eugene Charniak},
  TITLE = {Automatic compensation for parser figure-of-merit flaws},
  BOOKTITLE = {Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics (ACL'99)},
  YEAR = {1999},
  ISBN = {1-55860-609-3},
  PAGES = {513--518},
  LOCATION = {College Park, Maryland},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Morristown, NJ},
  URL = {http://acl.ldc.upenn.edu/P/P99/P99-1066.pdf}
}

@INPROCEEDINGS{caraballoec99,
  AUTHOR = {Sharon A. Caraballo and Eugene Charniak},
  TITLE = {Determining the Specificity of Nouns from Text},
  BOOKTITLE = {Proceedings of the Conference on Empirical Methods
                  in Natural Language Processing (EMNLP-99)},
  YEAR = {1999},
  PS = {http://www.cs.brown.edu/research/ai/publications/sc-emnlp99.ps}
}

@ARTICLE{Caraballo98,
  AUTHOR = {Sharon Caraballo and Eugene Charniak},
  TITLE = {New Figures of Merit for Best-First Probabalistic Chart Parsing},
  JOURNAL = {Computational Linguistics},
  VOLUME = 24,
  NUMBER = 2,
  YEAR = 1998,
  PAGES = {275-298},
  PDF = {http://acl.ldc.upenn.edu/J/J98/J98-2004.pdf}
}

@INPROCEEDINGS{Caraballo96,
  AUTHOR = {Sharon Caraballo and Eugene Charniak},
  TITLE = {Figures of Merit for Best-First Probabilistic
                  Parsing},
  BOOKTITLE = {Proceedings of the Conference on Empirical Methods
                  in Natural Language Processing (EMNLP'96)},
  YEAR = 1996,
  PAGES = {127-132},
  ABSTRACT = {Best-first parsing methods for natural language try to parse efficiently by considering the most likely constituents first. Some figure 
of merit is needed by which to compare the likelihood of constituents, and the choice of this figure has a substantial impact on the 
efficiency of the parser. While several parsers described in the literature have used such techniques, there is no published data on 
their efficacy, much less attempts to judge their relative merits. We propose and evaluate several figures of merit for best-first 
parsing.},
  KEYWORDS = {{parsing}, {nlp}},
  TECHREPORT = {http://www.cs.brown.edu/research/pubs/techreports/reports/CS-96-12.html},
  PDF = {http://acl.ldc.upenn.edu/W/W96/W96-0212.pdf}
}

@TECHREPORT{carroll92two,
  AUTHOR = {Glenn Carroll and Eugene Charniak},
  TITLE = {Two Experiments on Learning Probabilistic Dependency Grammars from Corpora},
  NUMBER = {CS-92-16},
  YEAR = {1992},
  INSTITUTION = {Brown University},
  ADDRESS = {Providence, RI, USA},
  URL = {http://www.cs.brown.edu/publications/techreports/reports/CS-92-16.html},
  ABSTRACT = {We present a scheme for learning probabilistic dependency grammars from positive training examples plus constraints on rules. In particular, we present the results of two experiments. 
The first, in which the constraints were minimal, was unsuccessful. The second, with significant constraints, was successful within the bounds of the task we had set.}
}

@TECHREPORT{Carroll94,
  AUTHOR = {Glenn Carroll and Eugene Charniak},
  TITLE = {Combining Grammars For Improved Learning},
  INSTITUTION = {Department of Computer Science, Brown University},
  NUMBER = {CS-94-08},
  MONTH = FEB,
  YEAR = {1994},
  PS = {http://bllip.cs.brown.edu/papers/cs94-08.ps},
  URL = {http://bllip.cs.brown.edu/papers/cs94-08.pdf},
  DOCUMENTURL = {http://www.cs.brown.edu/research/pubs/techreports/reports/CS-94-08.html},
  ABSTRACT = {We report experimental work on improving learning
         methods for probabilistic context-free grammars
         (PCFGs). From stacked regression we borrow the basic
         idea of combining grammars. Smoothing, a
         domain-independent method for combining grammars, does
         not offer noticeable performance gains. However, PCFGs
         allow much tighter, domain-dependent coupling, and we
         show that this maybe exploited for significant
         performance gains. Finally, we compare two strategies
         for acquiring the varying grammars needed for any
         combining method. We suggest that an unorthodox
         strategy, ``leave-one-in'' learning, is more effective
         than the more familiar ``leave-one-out''.}
}

@INPROCEEDINGS{charniak-EtAl:2006:HLT-NAACL06-Main,
  AUTHOR = {Charniak, Eugene  and  Johnson, Mark  and  Elsner, Micha  and  Austerweil, Joseph  and  Ellis, David  and  Haxton, Isaac  
and  Hill, Catherine  and  Shrivaths, R.  and  Moore, Jeremy  and  Pozar, Michael  and  Vu, Theresa},
  TITLE = {Multilevel Coarse-to-Fine PCFG Parsing},
  BOOKTITLE = {Proceedings of the Human Language Technology Conference of the NAACL (HLT-NAACL'06)},
  MONTH = {June},
  YEAR = {2006},
  ADDRESS = {New York City, USA},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {168--175},
  URL = {http://www.aclweb.org/anthology/N/N06/N06-1022},
  SLIDES = {http://www.cs.brown.edu/people/melsner/naacl-06-slides.pdf}
}

@INPROCEEDINGS{charniak-goldwater-johnson:1998:Very-Large-Corpora,
  AUTHOR = {Eugene Charniak and Sharon Goldwater and Mark Johnson},
  TITLE = {Edge-Based Best-First Chart Parsing},
  BOOKTITLE = {Sixth Workshop on Very Large Corpora},
  YEAR = 1998,
  PAGES = {127--133},
  PDF = {http://acl.ldc.upenn.edu/W/W98/W98-1115.pdf}
}

@INPROCEEDINGS{Charniak:2009:EACL,
  AUTHOR = {Charniak, Eugene and Elsner, Micha},
  TITLE = {EM Works for Pronoun Anaphora Resolution},
  BOOKTITLE = {Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics (EACL-09)},
  YEAR = {2009},
  ADDRESS = {Athens, Greece},
  PDF = {http://bllip.cs.brown.edu/papers/ec-eacl09.pdf}
}

@INPROCEEDINGS{charniak-johnson:2005:ACL,
  AUTHOR = {Charniak, Eugene  and  Johnson, Mark},
  TITLE = {Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking},
  BOOKTITLE = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05)},
  MONTH = {June},
  YEAR = {2005},
  ADDRESS = {Ann Arbor, Michigan},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {173--180},
  URL = {http://www.aclweb.org/anthology/P/P05/P05-1022}
}

@INPROCEEDINGS{charniak-knight-yamada:2003:MT_SUMMIT_IX,
  AUTHOR = {Charniak, Eugene and Knight, Kevin and Yamada, Kenji},
  TITLE = {Syntax-based Language Models for Statistical Machine Translation},
  BOOKTITLE = {Proceedings of the Ninth Machine Translation Summit of the International Association for Machine Translation},
  YEAR = 2003,
  MONTH = {September},
  ADDRESS = {New Orleans, Louisiana},
  URL = {http://www.amtaweb.org/summit/MTSummit/FinalPapers/21-Charniak-final.pdf}
}

@INPROCEEDINGS{Charniak-Johnson:2001:NAACL,
  AUTHOR = {Eugene Charniak and Mark Johnson},
  TITLE = {Edit Detection and Parsing for Transcribed Speech},
  BOOKTITLE = {Proceedings of the Second Conference of the North American chapter of the Association for Computational Linguistics (NAACL '01)},
  YEAR = {2001},
  URL = {http://acl.ldc.upenn.edu/N/N01/N01-1016.pdf}
}

@INPROCEEDINGS{charniak_ACL_2001,
  AUTHOR = {Charniak, Eugene},
  TITLE = {Immediate-Head Parsing for Language Models},
  BOOKTITLE = {Proceedings of 39th Annual Meeting of the Association for Computational Linguistics},
  YEAR = 2001,
  PAGES = {124--131},
  URL = {http://acl.ldc.upenn.edu/acl2001/MAIN/charniak.pdf},
  PS = {http://acl.ldc.upenn.edu/acl2001/MAIN/charniak.ps}
}

@INPROCEEDINGS{DBLP:conf/ai/Charniak00,
  AUTHOR = {Eugene Charniak},
  TITLE = {Parsing to Meaning, Statistically.},
  BOOKTITLE = {Canadian Conference on AI},
  YEAR = {2000},
  PAGES = {442},
  PDF = {http://www.springerlink.com/content/0a2c27tu257kaqy9/fulltext.pdf}
}

@INPROCEEDINGS{charniak:2001:NACL,
  AUTHOR = {Eugene Charniak},
  TITLE = {Unsupervised Learning of Name Structure From Coreference Data},
  BOOKTITLE = {Second Meeting of the North American Chapter of the Association for Computational Linguistics (NACL-01)},
  YEAR = 2001,
  PDF = {http://acl.ldc.upenn.edu/N/N01/N01-1007.pdf}
}

@INPROCEEDINGS{Charniak:2000:NAACL,
  AUTHOR = {Eugene Charniak},
  TITLE = {A maximum-entropy-inspired parser},
  BOOKTITLE = {Proceedings of the first conference on North American chapter of the Association for Computational Linguistics},
  YEAR = {2000},
  PAGES = {132--139},
  LOCATION = {Seattle, Washington},
  PUBLISHER = {Morgan Kaufmann Publishers Inc.},
  ADDRESS = {San Francisco, CA, USA},
  URL = {http://acl.ldc.upenn.edu/A/A00/A00-2018.pdf},
  TECHREPORT = {ftp://ftp.cs.brown.edu/pub/techreports/99/cs99-12.ps.Z}
}

@INPROCEEDINGS{ecaltun-anlpnaacl00,
  AUTHOR = {Eugene Charniak and Yasemin Altun and Rodrigo de Salvo Braz and Benjamin Garrett and Margaret Kosmala and Tomer Moscovich and Lixin Pang and Changbee Pyo and Ye Sun and Wei Wy and Z. Yang and S. Zeller and L. Zorn},
  TITLE = {Reading Comprehension Programs in a Statistical-Language-Processing Class},
  BOOKTITLE = {In ANLP/NAACL Workshop on Reading Comprehension Tests as Evaluation for Computer-Based Language Understanding Systems (ANLP/NAACL-00)},
  YEAR = {2000},
  URL = {http://acl.ldc.upenn.edu/W/W00/W00-0601.pdf}
}

@ARTICLE{charniak97statistical,
  AUTHOR = {Eugene Charniak},
  TITLE = {Statistical Techniques for Natural Language Parsing},
  JOURNAL = {AI Magazine},
  VOLUME = {18},
  NUMBER = {4},
  PAGES = {33-44},
  YEAR = {1997},
  PS = {http://bllip.cs.brown.edu/papers/charniak97statistical.ps},
  URL = {http://bllip.cs.brown.edu/papers/charniak97statistical.pdf}
}

@INPROCEEDINGS{Charniak97,
  AUTHOR = {Eugene Charniak},
  TITLE = {Statistical Parsing with a Context-Free Grammar and Word Statistics},
  BOOKTITLE = {Proceedings of AAAI},
  PAGES = {598--603},
  YEAR = 1997,
  PS = {http://bllip.cs.brown.edu/papers/aaai97.ps},
  URL = {http://bllip.cs.brown.edu/papers/aaai97.pdf},
  ABSTRACT = {We describe a parsing system based upon a language model for English that is, in turn, based upon assigning probabilities to possible parses for a sentence. This model is used in a parsing system by finding the parse for the sentence with the highest probability. This system outperforms previous schemes. As this is the third in a series of parsers by different authors that are similar enough to invite detailed comparisons but different enough to give rise to different levels of performance, we also report on some experiments designed to identify what aspects of these systems best explain their relative performance.},
  TECHREPORT = {ftp://ftp.cs.brown.edu/pub/techreports/95/cs95-28.ps.Z}
}

@INPROCEEDINGS{ec96,
  AUTHOR = {Eugene Charniak},
  TITLE = {Tree-bank Grammars},
  BOOKTITLE = {Proceedings of the Eleventh National Conference on Artificial Intelligence (AAAI-96)},
  YEAR = {1996},
  ABSTRACT = {By a ``tree-bank grammar'' we mean a context-free grammar created by reading the production rules directly from hand-parsed sentences in a tree bank. Common wisdom has it that such grammars do not perform well, though we know of no published data on the issue. The primary purpose of this paper is to show that the common wisdom is wrong. In particular we present results on a tree-bank grammar based on the Penn Wall Street Journal tree bank. To the best of our knowledge, this grammar out-performs all other non-word-based statistical parsers/grammars on this corpus. That is, it out-performs parsers that consider the input as a string of tags and ignore the actual words of the corpus.},
  TECHREPORT = {ftp://ftp.cs.brown.edu/pub/techreports/96/cs96-02.ps.Z}
}

@ARTICLE{charniak96taggers,
  AUTHOR = {Eugene Charniak and Glenn Carroll and John Adcock and Anthony R. Cassandra and Yoshihiko Gotoh and Jeremy Katz and Michael L. Littman and John McCann},
  TITLE = {Taggers for Parsers},
  JOURNAL = {Artificial Intelligence},
  VOLUME = {85},
  NUMBER = {1-2},
  PAGES = {45-57},
  YEAR = {1996},
  ABSTRACT = {We consider what tagging models are most appropriate as front ends for probabilistic context-free-grammar parsers. In particular we ask if using a tagger that returns more than one tag, a ``multple tagger,'' improves parsing performance. Our conclusion is somewhat surprising: single tag Markov-model taggers are quite adequate for the task. First of all, parsing accuracy, as measured by the correct assignment of parts of speech to words, does not increase significantly when parsers select the tags themselves. In addition, the work required to parse a sentence goes up with increasing tag ambiguity, though not as much as one might expect. Thus, for the moment, single taggers are the best taggers.},
  PS = {http://www.cs.brown.edu/people/ec/papers/tagforpar.ps},
  TECHREPORT = {ftp://ftp.cs.brown.edu/pub/techreports/94/cs94-06.ps.Z}
}

@TECHREPORT{charniak96expectedfrequency,
  AUTHOR = {Eugene Charniak},
  TITLE = {Expected-Frequency Interpolation},
  NUMBER = {CS-96-37},
  INSTITUTION = {Brown University},
  ADDRESS = {Providence, RI},
  YEAR = {1996},
  DOCUMENTURL = {http://www.cs.brown.edu/publications/techreports/reports/CS-96-37.html},
  ABSTRACT = {Expected-frequency interpolation is a technique for improving the performance of deleted interpolation smoothing. It allows a system to 
make finer-grained estimates of how often one would expect to see a particular combination of events than is possible with traditional 
frequency interpolation. This allows the system to better weigh the emphasis given to the various probability distributions being mixed. 
We show that more traditional frequency interpolation, based solely on the frequency of conditioning events, can lead to some anomalous 
results. We then show that while the equations for expected-frequency interpolation are not exact, they are close, depending on how well 
some seemingly reasonable assumptions hold. We then present an experiment in which the introduction of expected-frequency interpolation 
to a statistical parsing system improved performance by .4\% with essentially no extra work, and essentially no change in the workings of 
the system. We also note that even before the change, the system in question was the top performer at its task, so a .4\% improvement was 
well worth obtaining.}
}

@TECHREPORT{charniak95,
  AUTHOR = {Eugene Charniak},
  TITLE = {Parsing with context-free grammars and word statistics},
  NUMBER = {CS-95-28},
  INSTITUTION = {Brown University},
  ADDRESS = {Providence, RI},
  YEAR = {1995},
  DOCUMENTURL = {ftp://ftp.cs.brown.edu/pub/techreports/95/cs95-28.ps.Z},
  ABSTRACT = {We present a language model in which the probability of a sentence is the sum of the individual parse probabilities, and these are calculated using a probabilistic context-free grammar (PCFG) plus statistics on individual words and how they fit into parses. We have used the model to improve syntactic disambiguation. After training on Wall Street Journal (WSJ) text we tested on about 200 WSJ sentence restricted to the 5400 most common words from our training. We observed a 41\% reduction in bracket-crossing errors compared to the performance of our PCFG without the use of the word statistics.}
}

@TECHREPORT{charniak94taggers,
  AUTHOR = {Charniak, Eugene and Carroll, Glenn and Adcock, John and Cassandra, Antony and Gotoh, Yoshihiko and Katz, Jeremy and Littman, Michael and McCann, John},
  TITLE = {Expected-Frequency Interpolation},
  NUMBER = {CS-94-06},
  INSTITUTION = {Brown University},
  ADDRESS = {Providence, RI},
  YEAR = {1994},
  DOCUMENTURL = {ftp://ftp.cs.brown.edu/pub/techreports/94/cs94-06.ps.Z}
}

@TECHREPORT{charniak-carroll94,
  AUTHOR = {Eugene Charniak and Glenn Carroll},
  TITLE = {Context-Sensitive Statistics for Improved Grammatical Language Models},
  NUMBER = {CS-94-07},
  INSTITUTION = {Brown University},
  ADDRESS = {Providence, RI},
  YEAR = {1994},
  DOCUMENTURL = {http://www.cs.brown.edu/research/pubs/techreports/reports/CS-94-07.html},
  ABSTRACT = {We develop a language model using probabilistic context-free grammars (PCFGs) that is ``pseudo context-sensitive'' in that the 
probability that a non-terminal \$N\$ expands using a rule \$r\$ depends on \$N\$'s parent. We derive the equations for estimating the 
necessary probabilities using a variant of the inside-outside algorithm. We give experimental results showing that, beginning with a 
high-performance PCFG, one can develop a pseudo PCSG that yields significant performance gains. Analysis shows that the benefits from the 
context-sensitive statistics are localized, suggesting that we can use them to extend the original PCFG. Experimental results confirm that 
this is both feasible and the resulting grammar retains the performance gains. This implies that our scheme may be useful as a novel method 
for PCFG induction.},
  PS = {ftp://ftp.cs.brown.edu/pub/techreports/94/cs94-07.ps.Z}
}

@INPROCEEDINGS{charniak93equations,
  AUTHOR = {Eugene Charniak and Curtis Hendrickson and Neil Jacobson and Mike Perkowitz},
  TITLE = {Equations for Part-of-Speech Tagging},
  BOOKTITLE = {National Conference on Artificial Intelligence},
  PAGES = {784-789},
  YEAR = {1993},
  PS = {http://www.cs.brown.edu/people/ec/papers/equfortag.ps},
  ABSTRACT = {We derive from first principles the basic equations for a few of the basic hidden-Markov-model word taggers as well as equations for other models which may be novel (the descriptions in previous papers being too spare to be sure). We give performance results for all of the models. The results from our best model (96.45\% on an unused test sample from the Brown corpus with 181 distinct tags) is on the upper edge of reported results. We also hope these results clear up some confusion in the literature about the best equations to use. However, the major purpose of this paper is to show how the equations for a variety of models may be derived and thus encourage future authors to give the equations for their model and the derivations thereof.}
}

@BOOK{Charniak93,
  AUTHOR = {Eugene Charniak},
  TITLE = {Statistical Language Learning},
  PUBLISHER = {The MIT Press},
  YEAR = 1993,
  ADDRESS = {Cambridge, Massachusetts},
  HTTP = {http://books.google.com/books?vid=ISBN0262531410&id=ps3mqZANrHUC&pg=PP1&lpg=PP1&ots=XsOagonoJy&dq=%22statistical+language+learning%22&sig=dbPE4N0egEpG3G4NxqtfxoszL8M}
}

@TECHREPORT{ec90-13,
  AUTHOR = {Robert P. Goldman and Eugene Charniak},
  TITLE = {A Probabilistic Approach to Text Understanding},
  NUMBER = {CS-90-13},
  INSTITUTION = {Brown University},
  ADDRESS = {Providence, RI},
  YEAR = {1990},
  DOCUMENTURL = {http://www.cs.brown.edu/research/pubs/techreports/reports/CS-90-13.html},
  ABSTRACT = {We discuss a new framework for text understanding. Three major design decisions characterize this approach. First, we take the problem of text understanding to be a particular case of the general problem of abductive inference: reasoning from effects to causes. Second, we use probability theory to handle the uncertainty that arises in abductive inference in general and natural language understanding in particular. Finally, we treat all aspects of the text-understanding problem in a unified way. All aspects of natural language processing are treated in the same framework, allowing us to integrate syntactic, semantic and pragmatic constraints. In order to apply probability theory to this problem, we have developed a probabilistic model of text understanding. To make it practical to use this model, we have devised a way of incrementally constructing and evaluating belief networks that is applicable to other abduction problems. We have written a program, Wimp3, to experiment with this framework.}
}

@INPROCEEDINGS{Charniak:2010:TNP:1870658.1870724,
  AUTHOR = {Charniak, Eugene},
  TITLE = {Top-down nearly-context-sensitive parsing},
  BOOKTITLE = {Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing},
  SERIES = {EMNLP '10},
  YEAR = {2010},
  LOCATION = {Cambridge, Massachusetts},
  PAGES = {674--683},
  NUMPAGES = {10},
  URL = {http://dl.acm.org/citation.cfm?id=1870658.1870724},
  ACMID = {1870724},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Stroudsburg, PA, USA}
}

@ARTICLE{Charniak:2011:BSI:2077692.2077693,
  AUTHOR = {Charniak, Eugene},
  TITLE = {The brain as a statistical inference engine-and you can too},
  JOURNAL = {Comput. Linguist.},
  ISSUE_DATE = {December 2011},
  VOLUME = {37},
  NUMBER = {4},
  ISSN = {0891-2017},
  PAGES = {643--655},
  NUMPAGES = {13},
  URL = {http://dx.doi.org/10.1162/COLI_a_00080},
  DOI = {10.1162/COLI_a_00080},
  ACMID = {2077693},
  PUBLISHER = {MIT Press},
  ADDRESS = {Cambridge, MA, USA}
}

@ARTICLE{Chi-Geman:CL:1998,
  AUTHOR = {Zhiyi Chi and Stuart Geman},
  TITLE = {Estimation of probabilistic context-free grammars},
  JOURNAL = {Computational Linguistics},
  VOLUME = {24},
  NUMBER = {2},
  YEAR = {1998},
  ISSN = {0891-2017},
  PAGES = {299--305},
  PUBLISHER = {MIT Press},
  ADDRESS = {Cambridge, MA, USA},
  URL = {http://acl.ldc.upenn.edu/J/J98/J98-2005.pdf}
}

@INPROCEEDINGS{ciaramita-johnson:2004:Senseval-3,
  AUTHOR = {Ciaramita, Massimiliano  and  Johnson, Mark},
  TITLE = {Multi-component Word Sense Disambiguation},
  BOOKTITLE = {Senseval-3: Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text},
  EDITOR = {Rada Mihalcea and Phil Edmonds},
  YEAR = 2004,
  MONTH = {July},
  ADDRESS = {Barcelona, Spain},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {97--100},
  URL = {http://acl.ldc.upenn.edu/acl2004/senseval/pdf/ciaramita.pdf}
}

@INPROCEEDINGS{conf/ijcai/CiaramitaHJ03,
  TITLE = {Hierarchical Semantic Classification: Word Sense
		 Disambiguation with World Knowledge},
  AUTHOR = {Massimiliano Ciaramita and Thomas Hofmann and Mark
		 Johnson},
  BOOKTITLE = {{IJCAI}-03, Proceedings of the Eighteenth
		 International Joint Conference on Artificial
		 Intelligence, Acapulco, Mexico, August 9-15, 2003},
  PUBLISHER = {Morgan Kaufmann},
  YEAR = {2003},
  EDITOR = {Georg Gottlob and Toby Walsh},
  PAGES = {817--822},
  URL = {http://bllip.cs.brown.edu/papers/massi-ijcai03.pdf},
  PS = {http://bllip.cs.brown.edu/papers/massi-ijcai03.ps}
}

@INPROCEEDINGS{ciaramita-johnson:2003:EMNLP,
  AUTHOR = {Ciaramita, Massimiliano and Johnson, Mark},
  TITLE = {Supersense Tagging of Unknown Nouns in WordNet},
  BOOKTITLE = {Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing (EMNLP-03)},
  YEAR = 2003,
  PAGES = {168--175},
  PDF = {http://acl.ldc.upenn.edu/W/W03/W03-1022.pdf}
}

@INPROCEEDINGS{ciaramita:2002:LEX,
  AUTHOR = {Ciaramita, Massimiliano},
  TITLE = {Boosting automatic lexical acquisition with morphological information},
  BOOKTITLE = {Unsupervised Lexical Acquisition: Proceedings of the Workshop of the ACL Special Interest Group on the Lexicon (SIGLEX)},
  YEAR = 2002,
  MONTH = {July},
  ADDRESS = {Philadelphia},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {17--25},
  PDF = {http://acl.ldc.upenn.edu/acl2002/LEX/pdfs/LEX006.pdf},
  PS = {http://acl.ldc.upenn.edu/acl2002/LEX/ps/LEX006.ps}
}

@INPROCEEDINGS{ciaramita-johnson:2000:COLING,
  AUTHOR = {Ciaramita, Massimiliano and Johnson, Mark},
  TITLE = {Explaining away ambiguity: Learning verb selectional preference with Bayesian networks},
  BOOKTITLE = {Proceedings of the 18th International Conference on Computational Linguistics},
  YEAR = {2000},
  URL = {http://acl.ldc.upenn.edu/C/C00/C00-1028.pdf}
}

@INPROCEEDINGS{elsner-schudy09,
  AUTHOR = {Elsner, Micha and Schudy, Warren},
  TITLE = {Bounding and Comparing Methods for Correlation Clustering Beyond ILP},
  BOOKTITLE = {Proceedings of the NAACL/HLT 2009 Workshop on Integer Linear Programming for Natural Language Processing (ILP-NLP '09)},
  MONTH = {June},
  YEAR = {2009},
  ADDRESS = {Boulder, Colorado},
  PDF = {http://bllip.cs.brown.edu/papers/melsner-ilpnlp.pdf}
}

@INPROCEEDINGS{elsner-EtAl:2005:IWPT,
  AUTHOR = {Elsner, Micha  and  Swift, Mary  and  Allen, James  and  Gildea, Daniel},
  TITLE = {Online Statistics for a Unification-Based Dialogue Parser},
  BOOKTITLE = {Proceedings of the Ninth International Workshop on Parsing Technology (IWPT'05)},
  MONTH = {October},
  YEAR = {2005},
  ADDRESS = {Vancouver, British Columbia},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {198--199},
  URL = {http://www.aclweb.org/anthology/W/W05/W05-1526},
  POSTER = {http://www.cs.brown.edu/people/melsner/iwpt-05-poster.pdf}
}

@INPROCEEDINGS{elsner-EtAl:2007:NAACL,
  AUTHOR = {Elsner, Micha  and  Austerweil, Joseph and Charniak, Eugene},
  TITLE = {A Unified Local and Global Model for Discourse Coherence},
  BOOKTITLE = {Proceedings of HLT-NAACL '07},
  MONTH = {April},
  YEAR = {2007},
  ADDRESS = {Rochester, New York},
  PUBLISHER = {Association for Computational Linguistics},
  URL = {http://cs.brown.edu/people/melsner/order.pdf},
  SLIDES = {http://cs.brown.edu/people/melsner/order-slides.pdf}
}

@TECHREPORT{elsner-2007,
  AUTHOR = {Elsner, Micha and Charniak, Eugene},
  TITLE = {A Generative Discourse-New Model for Text Coherence},
  NUMBER = {CS-07-04},
  YEAR = {2007},
  INSTITUTION = {Brown University},
  ADDRESS = {Providence, RI, USA},
  URL = {ftp://ftp.cs.brown.edu/pub/techreports/07/cs07-04.pdf},
  ABSTRACT = {Recent models of document coherence have focused on the
referents of noun phrases, ignoring their syntax. However, syntax
depends on discourse function; NPs which introduce new entities are
often more complex. We develop a generative model for NP syntax which
describes this difference. It can be used to model discourse coherence
in the Wall Street Journal; combining it with the local coherence
model of Elsner ('07) yields substantial improvements. Our model is
competitive with previous systems on the discourse-new detection task;
its performance is comparable to Uryupina ('03).}
}

@INPROCEEDINGS{elsner-charniak:2008:ACLMain,
  AUTHOR = {Elsner, Micha  and  Charniak, Eugene},
  TITLE = {You Talking to Me? A Corpus and Algorithm for Conversation Disentanglement},
  BOOKTITLE = {Proceedings of ACL-08: HLT},
  MONTH = {June},
  YEAR = {2008},
  ADDRESS = {Columbus, Ohio},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {834--842},
  URL = {http://www.aclweb.org/anthology/P/P08/P08-1095},
  SLIDES = {http://cs.brown.edu/people/melsner/acl-08-slides.pdf}
}

@INPROCEEDINGS{elsner-charniak:2008:ACLShort,
  AUTHOR = {Elsner, Micha  and  Charniak, Eugene},
  TITLE = {Coreference-inspired Coherence Modeling},
  BOOKTITLE = {Proceedings of ACL-08: HLT, Short Papers},
  MONTH = {June},
  YEAR = {2008},
  ADDRESS = {Columbus, Ohio},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {41--44},
  URL = {http://www.aclweb.org/anthology/P/P08/P08-2011},
  POSTER = {http://cs.brown.edu/people/melsner/acl-08-poster.pdf}
}

@INPROCEEDINGS{Elsner09,
  AUTHOR = {Elsner, Micha and Charniak, Eugene and Johnson, Mark},
  TITLE = {Structured Generative Models for Unsupervised Named-Entity Clustering},
  BOOKTITLE = {Proceedings of NAACL-09: HLT},
  MONTH = {June},
  YEAR = {2009},
  ADDRESS = {Boulder, Colorado},
  PUBLISHER = {Association for Computational Linguistics},
  PDF = {http://bllip.cs.brown.edu/papers/melsner-naacl09.pdf}
}

@INPROCEEDINGS{Elsner10,
  AUTHOR = {Elsner, Micha and Charniak, Eugene},
  TITLE = {The Same-head Heuristic for Coreference},
  BOOKTITLE = {Proceedings of ACL 10},
  MONTH = {July},
  YEAR = {2010},
  ADDRESS = {Uppsala, Sweden},
  PUBLISHER = {Association for Computational Linguistics},
  PDF = {http://bllip.cs.brown.edu/papers/melsner-acl10.pdf}
}

@ARTICLE{Elsner:2010:DC:1950488.1950492,
  AUTHOR = {Elsner, Micha and Charniak, Eugene},
  TITLE = {Disentangling chat},
  JOURNAL = {Comput. Linguist.},
  ISSUE_DATE = {September 2010},
  VOLUME = {36},
  NUMBER = {3},
  ISSN = {0891-2017},
  PAGES = {389--409},
  NUMPAGES = {21},
  URL = {http://dx.doi.org/10.1162/coli_a_00003},
  DOI = {10.1162/coli_a_00003},
  ACMID = {1950492},
  PUBLISHER = {MIT Press},
  ADDRESS = {Cambridge, MA, USA}
}

@INPROCEEDINGS{Elsner:2011:DCL:2002472.2002622,
  AUTHOR = {Elsner, Micha and Charniak, Eugene},
  TITLE = {Disentangling chat with local coherence models},
  BOOKTITLE = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1},
  SERIES = {HLT '11},
  YEAR = {2011},
  ISBN = {978-1-932432-87-9},
  LOCATION = {Portland, Oregon},
  PAGES = {1179--1189},
  NUMPAGES = {11},
  URL = {http://dl.acm.org/citation.cfm?id=2002472.2002622},
  ACMID = {2002622},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Stroudsburg, PA, USA}
}

@INPROCEEDINGS{Elsner:2011:LFD:2107679.2107686,
  AUTHOR = {Elsner, Micha and Santhanam, Deepak},
  TITLE = {Learning to fuse disparate sentences},
  BOOKTITLE = {Proceedings of the Workshop on Monolingual Text-To-Text Generation},
  SERIES = {MTTG '11},
  YEAR = {2011},
  ISBN = {9781937284053},
  LOCATION = {Portland, Oregon},
  PAGES = {54--63},
  NUMPAGES = {10},
  URL = {http://dl.acm.org/citation.cfm?id=2107679.2107686},
  ACMID = {2107686},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Stroudsburg, PA, USA}
}

@INPROCEEDINGS{Eisner:2011:EEG:2002736.2002764,
  AUTHOR = {Eisner, Micha and Charniak, Eugene},
  TITLE = {Extending the entity grid with entity-specific features},
  BOOKTITLE = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2},
  SERIES = {HLT '11},
  YEAR = {2011},
  ISBN = {978-1-932432-88-6},
  LOCATION = {Portland, Oregon},
  PAGES = {125--129},
  NUMPAGES = {5},
  URL = {http://dl.acm.org/citation.cfm?id=2002736.2002764},
  ACMID = {2002764},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Stroudsburg, PA, USA}
}

@INPROCEEDINGS{engel-charniak-johnson:2002:EMNLP,
  AUTHOR = {Donald Engel and Eugene Charniak and Mark Johnson},
  TITLE = {Parsing and Disfluency Placement},
  BOOKTITLE = {Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002)},
  YEAR = 2002,
  PAGES = {49--54},
  PDF = {http://acl.ldc.upenn.edu/W/W02/W02-1007.pdf}
}

@INPROCEEDINGS{ersan-charniak:1995:LNLP,
  AUTHOR = {Ersan, Murat and Charniak, Eugene},
  EDITOR = {Wermter, Stefan and Riloff, Ellen and Scheler, Gabriele},
  TITLE = {A statistical syntactic disambiguation program and what it learns},
  BOOKTITLE = {Symbolic, Connectionist, and Statistical Approaches to Learning for Natural Language Processing},
  YEAR = {1995},
  TECHREPORT = {ftp://ftp.cs.brown.edu/pub/techreports/95/cs95-29.ps.Z}
}

@INPROCEEDINGS{fox:2002:emnlp,
  AUTHOR = {Fox, Heidi},
  TITLE = {Phrasal Cohesion and Statistical Machine Translation},
  BOOKTITLE = {Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002)},
  MONTH = {July},
  YEAR = {2002},
  ADDRESS = {Philadelphia, Pennsylvania},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {304--311},
  URL = {http://acl.ldc.upenn.edu/W/W02/W02-1039.pdf}
}

@INPROCEEDINGS{fox:2005:Student,
  AUTHOR = {Fox, Heidi},
  TITLE = {Dependency-Based Statistical Machine Translation},
  BOOKTITLE = {Proceedings of the ACL Student Research Workshop},
  MONTH = {June},
  YEAR = {2005},
  ADDRESS = {Ann Arbor, Michigan},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {91--96},
  URL = {http://www.aclweb.org/anthology/P/P05/P05-2016.pdf}
}

@INPROCEEDINGS{gao-acl07,
  AUTHOR = {Jianfeng Gao and Galen Andrew and Mark Johnson and Kristina Toutanova},
  TITLE = {A Comparative Study of Parameter Estimation Methods for Statistical Natural Language Processing},
  BOOKTITLE = {Proceedings of the Association for Computational Linguistics (ACL'07)},
  YEAR = {2007}
}

@INPROCEEDINGS{ge98,
  AUTHOR = {Niyu Ge and John Hale and Eugene Charniak},
  TITLE = {A statistical approach to anaphora resolution},
  BOOKTITLE = {Proceedings of the Sixth Workshop on Very Large Corpora},
  YEAR = {1998},
  PAGS = {161--170},
  PUBLISHER = {Harcourt Brace},
  ADDRESS = {Orlando, Florida},
  URL = {http://www.cs.brown.edu/research/pubs/pdfs/1998/Ge-1998-SAA.pdf},
  ABSTRACT = {This paper presents an algorithm for identifying pronominal anaphora and two experiments based upon this algorithm. We incorporate multiple anaphora resolution factors into a 
statistical framework --- specifically the distance between the pronoun and the proposed antecedent, gender/number/animaticity of the proposed antecedent, governing head information and noun phrase 
repetition. We combine them into a single probability that enables us to identify the referent. Our first experiment shows the relative contribution of each source of information and 
demonstrates a success rate of 82.9\% for all sources combined. The second experiment investigates a method for unsupervised learning of gender/number/animaticity information. We present 
some experiments illustrating the accuracy of the method and note that with this information added, our pronoun resolution method achieves 84.2\% accuracy.}
}

@ARTICLE{geman-johnson:2003,
  AUTHOR = {Stuart Geman and Mark Johnson},
  TITLE = {Probability and statistics in computational linguistics, a brief review},
  JOURNAL = {Mathematical foundations of speech and language processing},
  VOLUME = {138},
  PAGES = {1--26},
  EDITOR = {Springer-Verlag},
  ADDRESS = {New York},
  YEAR = {2003},
  URL = {http://bllip.cs.brown.edu/papers/Review.pdf}
}

@INPROCEEDINGS{Geman02-acl,
  AUTHOR = {Stuart Geman and Mark Johnson},
  TITLE = {Dynamic programming for parsing and estimation of stochastic unification-based grammars},
  BOOKTITLE = {Proceedings of the 40th Annual Meeting on Association for Computational Linguistics (ACL'02)},
  YEAR = {2002},
  PAGES = {279--286},
  LOCATION = {Philadelphia, Pennsylvania},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Morristown, NJ, USA},
  URL = {http://acl.ldc.upenn.edu/P/P02/P02-1036.pdf}
}

@INPROCEEDINGS{gemanmj02-encyc,
  AUTHOR = {Stuart Geman and Mark Johnson},
  TITLE = {Probabilistic Grammars and their Applications},
  BOOKTITLE = {International Encyclopedia of the Social & Behavioral Sciences},
  EDITOR = {N.J. Smelser and P.B. Baltes},
  ADDRESS = {Pergamon, Oxford},
  YEAR = {2002},
  PAGES = {12075-12082},
  URL = {http://www.dam.brown.edu/people/geman/Papers/Encyclopedia-published.pdf}
}

@INPROCEEDINGS{genzel:2005:HLTEMNLP,
  AUTHOR = {Genzel, Dmitriy},
  TITLE = {Inducing a Multilingual Dictionary from a Parallel Multitext in Related Languages},
  BOOKTITLE = {Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing},
  MONTH = {October},
  YEAR = {2005},
  ADDRESS = {Vancouver, British Columbia, Canada},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {875-882},
  URL = {http://www.aclweb.org/anthology/H/H05/H05-1110}
}

@INPROCEEDINGS{Genzel:2003:EMNLP,
  AUTHOR = {Genzel, Dmitriy  and  Charniak, Eugene},
  TITLE = {Variation of Entropy and Parse Trees of Sentences as a Function of the Sentence Number},
  BOOKTITLE = {Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing (EMNLP'03)},
  EDITOR = {Michael Collins and Mark Steedman},
  URL = {http://www.aclweb.org/anthology/W03-1009.pdf},
  YEAR = 2003,
  PAGES = {65--72}
}

@INPROCEEDINGS{Genzel02Entropy,
  AUTHOR = {Dmitriy Genzel and Eugene Charniak},
  TITLE = {Entropy Rate Constancy in Text},
  YEAR = 2002,
  BOOKTITLE = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL-02)},
  PAGES = {00-00},
  URL = {http://www.aclweb.org/anthology/P02-1026.pdf}
}

@INPROCEEDINGS{goldwater07-bos,
  AUTHOR = {Sharon Goldwater and Thomas L. Griffiths and Mark Johnson},
  TITLE = {Distributional Cues to Word Segmentation: Context is Important},
  BOOKTITLE = {Proceedings of the 31st Boston University Conference on Language Development},
  YEAR = {2007},
  URL = {http://www.stanford.edu/~sgwater/papers/bucld07.pdf}
}

@INPROCEEDINGS{goldwater-griffiths-johnson:2005:NIPS,
  TITLE = {Interpolating between types and tokens by estimating power-law generators},
  AUTHOR = {Sharon Goldwater and Tom Griffiths and Mark Johnson},
  BOOKTITLE = {Advances in Neural Information Processing Systems 18},
  EDITOR = {Y. Weiss and B. Sch\"{o}lkopf and J. Platt},
  PUBLISHER = {MIT Press},
  ADDRESS = {Cambridge, MA},
  PAGES = {459--466},
  YEAR = {2006},
  PDF = {http://books.nips.cc/papers/files/nips18/NIPS2005_0333.pdf}
}

@INPROCEEDINGS{goldwater-griffiths-johnson:2006:COLACL,
  AUTHOR = {Goldwater, Sharon  and  Griffiths, Thomas L.  and  Johnson, Mark},
  TITLE = {Contextual Dependencies in Unsupervised Word Segmentation},
  BOOKTITLE = {Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association or Computational Linguistics (COLING_ACL'06)},
  MONTH = {July},
  YEAR = {2006},
  ADDRESS = {Sydney, Australia},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {673--680},
  URL = {http://www.aclweb.org/anthology/P/P06/P06-1085}
}

@INPROCEEDINGS{goldwater-mcclosky:2005:HLTEMNLP,
  AUTHOR = {Goldwater, Sharon  and  McClosky, David},
  TITLE = {Improving Statistical MT through Morphological Analysis},
  BOOKTITLE = {Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing 
(HLT-EMNLP'05)},
  MONTH = {October},
  YEAR = {2005},
  ADDRESS = {Vancouver, British Columbia, Canada},
  PAGES = {676--683},
  PUBLISHER = {Association for Computational Linguistics},
  URL = {http://www.aclweb.org/anthology/H/H05/H05-1085},
  PS = {http://cs.brown.edu/~dmcc/papers/sgwater-emnlp-2005.ps}
}

@INPROCEEDINGS{goldwater-johnson:2005:CoNLL,
  AUTHOR = {Goldwater, Sharon  and  Johnson, Mark},
  TITLE = {Representational Bias in Unsupervised Learning of Syllable Structure},
  BOOKTITLE = {Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005)},
  MONTH = {June},
  YEAR = {2005},
  ADDRESS = {Ann Arbor, Michigan},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {112--119},
  URL = {http://www.aclweb.org/anthology/W/W05/W05-0615}
}

@INPROCEEDINGS{goldwater-johnson:2004:SIGPHON,
  AUTHOR = {Goldwater, Sharon  and  Johnson, Mark},
  TITLE = {Priors in Bayesian Learning of Phonological Rules},
  BOOKTITLE = {Proceedings of the Seventh Meeting of the ACL Special Interest Group in Computational Phonology},
  YEAR = 2004,
  MONTH = {July},
  ADDRESS = {Barcelona, Spain},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {35--42},
  URL = {http://acl.ldc.upenn.edu/acl2004/sigphon/pdf/goldwater.pdf}
}

@INPROCEEDINGS{auh20mj03,
  AUTHOR = {Sharon Goldwater and Mark Johnson},
  TITLE = {Learning OT Constraint Rankings Using a Maximum Entropy Model},
  BOOKTITLE = {Proceedings of the Workshop on Variation within Optimality Theory},
  YEAR = {2003},
  ADDRESS = {Stockholm University},
  URL = {http://www.stanford.edu/~sgwater/papers/OTvar03.pdf},
  PS = {http://www.stanford.edu/~sgwater/papers/OTvar03.ps}
}

@INPROCEEDINGS{gregory-altun:2004:ACL,
  AUTHOR = {Gregory, Michelle  and  Altun, Yasemin},
  TITLE = {Using Conditional Random Fields to Predict Pitch Accents in Conversational Speech},
  BOOKTITLE = {Proceedings of the 42nd Meeting of the Association for Computational Linguistics (ACL'04), Main Volume},
  YEAR = 2004,
  MONTH = {July},
  ADDRESS = {Barcelona, Spain},
  PAGES = {677--683},
  URL = {http://acl.ldc.upenn.edu/P/P04/P04-1086.pdf}
}

@INPROCEEDINGS{gregory-johnson-charniak:2004:HLTNAACL,
  AUTHOR = {Gregory, Michelle and Johnson, Mark and Charniak, Eugene},
  TITLE = {Sentence-Internal Prosody Does not Help Parsing the Way Punctuation Does},
  BOOKTITLE = {HLT-NAACL 2004: Main Proceedings },
  EDITOR = {Susan Dumais, Daniel Marcu and Salim Roukos},
  YEAR = 2004,
  MONTH = {May 2 - May 7},
  ADDRESS = {Boston, Massachusetts, USA},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {81--88},
  PDF = {http://acl.ldc.upenn.edu/hlt-naacl2004/main/bib/50_Paper.pdf}
}

@INPROCEEDINGS{hale-EtAl:2006:COLACL,
  AUTHOR = {Hale, John  and  Shafran, Izhak  and  Yung, Lisa  and  Dorr, Bonnie J.  and  Harper, Mary  and  Krasnyanskaya, Anna  and  Lease, Matthew  and  Liu, Yang  and  Roark, Brian  and  Snover, Matthew  and  Stewart, Robin},
  TITLE = {PCFGs with Syntactic and Prosodic Indicators of Speech Repairs},
  BOOKTITLE = {Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (COLING-ACL'06)},
  MONTH = {July},
  YEAR = {2006},
  ADDRESS = {Sydney, Australia},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {161--168},
  URL = {http://www.aclweb.org/anthology/P/P06/P06-1021}
}

@TECHREPORT{halecharniak98,
  AUTHOR = {John Hale and Eugene Charniak},
  TITLE = {Getting Useful Gender Statistics from English Text},
  NUMBER = {CS-98-06},
  INSTITUTION = {Brown University},
  ADDRESS = {Providence, RI},
  YEAR = {1998},
  DOCUMENTURL = {http://www.cs.brown.edu/research/pubs/techreports/reports/CS-98-06.html},
  ABSTRACT = {Gender, understood as a lexical feature, is important for anaphora because it narrows down the number of possible referents 
involved in a typical pronoun resolution situation. This work describes an automatic method for obtaining reliable guesses about the gender 
of entities in a corpus using free text. By using a simple but unreliable anaphora algorithm repeatedly over a large corpus, the probable 
genders of referenced entities can be compiled and given a salience ranking. These statistics are an inexpensive way to add on gender-feature 
information to a statistical anaphora resolution algorithm.},
  PS = {ftp://ftp.cs.brown.edu/pub/techreports/98/cs98-06.ps.Z}
}

@INPROCEEDINGS{hall-johnson:2004:ACL,
  AUTHOR = {Hall, Keith B.  and  Johnson, Mark},
  TITLE = {Attention Shifting for Parsing Speech},
  BOOKTITLE = {Proceedings of the 42nd Meeting of the Association for Computational Linguistics (ACL'04), Main Volume},
  YEAR = 2004,
  MONTH = {July},
  ADDRESS = {Barcelona, Spain},
  PAGES = {40--46},
  PDF = {http://acl.ldc.upenn.edu/P/P04/P04-1006.pdf}
}

@INPROCEEDINGS{hall03,
  AUTHOR = {Keith Hall and Mark Johnson},
  TITLE = {Language modelling using efficient best-first bottom-up parsing},
  BOOKTITLE = {Automatic Speech Recognition and Understanding Workshop (ASRU)},
  YEAR = 2003,
  ORGANIZATION = {IEEE ASRU 2003},
  URL = {http://bllip.cs.brown.edu/papers/hall03.pdf}
}

@MASTERSTHESIS{Hall01-masters,
  AUTHOR = {Keith Hall},
  TITLE = {A Statistical Model of Nominal Anaphora},
  YEAR = 2001,
  SCHOOL = {Brown University},
  ADDRESS = {Providence, RI},
  URL = {http://www.cs.brown.edu/research/pubs/theses/masters/2001/kh.pdf}
}

@INPROCEEDINGS{conf/icml/HallH00,
  AUTHOR = {Keith Hall and Thomas Hofmann},
  TITLE = {Learning Curved Multinomial Subfamilies for Natural
         Language Processing and Information Retrieval},
  BOOKTITLE = {Proceedings of the Seventeenth International
         Conference on Machine Learning ({ICML} 2000), Stanford
         University, Stanford, {CA}, {USA}, June 29 - July 2,
         2000},
  PUBLISHER = {Morgan Kaufmann},
  YEAR = {2000},
  EDITOR = {Pat Langley},
  ISBN = {1-55860-707-2},
  PAGES = {351--358},
  URL = {http://www.clsp.jhu.edu/~khall/pubs/sphericalICML00.pdf}
}

@INPROCEEDINGS{headdeniii-charniak-johnson:2006:EMNLP,
  AUTHOR = {Headden III, William P.  and  Charniak, Eugene  and  Johnson, Mark},
  TITLE = {Learning Phrasal Categories},
  BOOKTITLE = {Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing},
  MONTH = {July},
  YEAR = {2006},
  ADDRESS = {Sydney, Australia},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {301--307},
  URL = {http://www.aclweb.org/anthology/W/W06/W06-1636}
}

@INPROCEEDINGS{headdeniii-mcclosky-charniak:2008:COLING,
  AUTHOR = {William P. Headden III and David McClosky and Eugene Charniak},
  TITLE = {Evaluating Unsupervised Part-of-Speech Tagging for Grammar Induction},
  BOOKTITLE = {Proceedings of the 22nd International Conference on Computational Linguistics (COLING'08)},
  MONTH = {August},
  YEAR = {2008},
  ADDRESS = {Manchester, UK},
  URL = {http://cs.brown.edu/~dmcc/papers/headdenw-coling-2008.pdf},
  PS = {http://cs.brown.edu/~dmcc/papers/headdenw-coling-2008.ps}
}

@INPROCEEDINGS{headdeniii-johnson-mcclosky:2009:NAACL,
  AUTHOR = {William P. Headden III and Mark Johnson and David McClosky},
  TITLE = {Improving Unsupervised Dependency Parsing with Richer Contexts and Smoothing},
  BOOKTITLE = {Proceedings of the Human Language Technology Conference of the NAACL, Main Conference (to appear)},
  MONTH = {May},
  YEAR = {2009},
  ADDRESS = {Boulder, Colorado}
}

@INPROCEEDINGS{hofmann-cai-ciaramita:2003:NIPS,
  AUTHOR = {Hofmann, Thomas and Cai, Lijuan and Ciaramita, Massimiliano},
  TITLE = {Learning with taxonomies: Classifying documents and words},
  BOOKTITLE = {Workshop on Syntax, Semantics and Statistics (NIPS-03).},
  YEAR = {2003},
  URL = {http://www.cog.brown.edu/~massi/nips_03.pdf}
}

@INPROCEEDINGS{johnson07-emnlp,
  AUTHOR = {Mark Johnson},
  TITLE = {Why Doesn't EM Find Good HMM POS-Taggers?},
  BOOKTITLE = {Proceedings of Empirical Methods in Natural Language Processing (EMNLP'07)},
  YEAR = {2007}
}

@INPROCEEDINGS{johnson07-acl,
  AUTHOR = {Mark Johnson},
  TITLE = {Transforming Projective Bilexical Dependency Grammars into Efficiently-Parsable CFGs with Unfold-Fold},
  BOOKTITLE = {Proceedings of the Association for Computational Linguistics (ACL'07)},
  YEAR = {2007}
}

@INPROCEEDINGS{johnson07-naacl,
  AUTHOR = {Mark Johnson and Thomas L. Griffiths and Sharon Goldwater},
  TITLE = {Bayesian inference for PCFGs via Markov chain Monte Carlo},
  BOOKTITLE = {Proceedings of the North American Conference on Computational Linguistics (NAACL'07)},
  YEAR = {2007},
  URL = {http://cocosci.berkeley.edu/tom/mcmc-pcfg.pdf}
}

@INPROCEEDINGS{johnson07-nips,
  AUTHOR = {Mark Johnson and Thomas L. Griffiths and Sharon Goldwater},
  TITLE = {Adaptor Grammars: a Framework for Specifying Compositional Nonparametric Bayesian Models},
  BOOKTITLE = {Advances in Neural Information Processing Systems 19},
  YEAR = {2007},
  URL = {http://www.stanford.edu/~sgwater/papers/nips07-adaptor.pdf}
}

@INPROCEEDINGS{johnson-charniak:2004:ACL,
  AUTHOR = {Johnson, Mark  and  Charniak, Eugene},
  TITLE = {A TAG-based noisy-channel model of speech repairs },
  BOOKTITLE = {Proceedings of the 42nd Meeting of the Association for Computational Linguistics (ACL'04)},
  YEAR = 2004,
  MONTH = {July},
  ADDRESS = {Barcelona, Spain},
  PAGES = {33--39},
  URL = {http://acl.ldc.upenn.edu/acl2004/main/pdf/30_pdf_2-col.pdf}
}

@INPROCEEDINGS{mkecml04-rtf,
  AUTHOR = {Mark Johnson and Eugene Charniak and Matthew Lease},
  TITLE = {An Improved Model For Recognizing Disfluencies in Conversational Speech},
  BOOKTITLE = {Rich Transcription 2004 Fall Workshop (RT-04F)},
  YEAR = {2004},
  URL = {../papers/rt04-paper.pdf}
}

@INPROCEEDINGS{conf/colt/Johnson03,
  TITLE = {Learning and Parsing Stochastic Unification-Based
		 Grammars},
  AUTHOR = {Mark Johnson},
  BOOKTITLE = {Computational Learning Theory and Kernel Machines,
		 16th Annual Conference on Computational Learning Theory
		 and 7th Kernel Workshop, {COLT}/Kernel 2003,
		 Washington, {DC}, {USA}, August 24-27, 2003,
		 Proceedings},
  PUBLISHER = {Springer},
  YEAR = {2003},
  VOLUME = {2777},
  EDITOR = {Bernhard Sch{\"o}lkopf and Manfred K. Warmuth},
  ISBN = {3-540-40720-0},
  PAGES = {671--683},
  SERIES = {Lecture Notes in Computer Science},
  URL = {http://www.cog.brown.edu:16080/~mj/papers/colt03.pdf}
}

@ARTICLE{johnson:2002:CL,
  AUTHOR = {Mark Johnson},
  TITLE = {The DOP Estimation Method is Biased and Inconsistent},
  JOURNAL = {Computational Linguistics},
  VOLUME = {28},
  NUMBER = {1},
  YEAR = {2002},
  PAGES = {71--76},
  URL = {http://acl.ldc.upenn.edu/J/J02/J02-1005.pdf}
}

@INPROCEEDINGS{johnson:2002:ACL,
  AUTHOR = {Johnson, Mark},
  TITLE = {A Simple Pattern-matching Algorithm for Recovering Empty Nodes and their Antecedents},
  BOOKTITLE = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL)},
  YEAR = 2002,
  PAGES = {136--143},
  URL = {http://acl.ldc.upenn.edu/acl2002/MAIN/pdfs/Main057.pdf},
  PS = {http://acl.ldc.upenn.edu/acl2002/MAIN/ps/Main057.ps}
}

@INPROCEEDINGS{mj01,
  AUTHOR = {Mark Johnson},
  TITLE = {Joint and Conditional Estimation of Tagging and Parsing Models},
  BOOKTITLE = {Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL-01)},
  YEAR = {2001},
  URL = {http://acl.ldc.upenn.edu/P/P01/P01-1042.pdf}
}

@INPROCEEDINGS{Johnson-Roark:2000:COLING,
  AUTHOR = {Mark Johnson and Brian Roark},
  TITLE = {Compact non-left-recursive grammars using the selective left-corner transform and factoring},
  BOOKTITLE = {Proceedings of the 18th conference on Computational linguistics (COLING '00)},
  YEAR = {2000},
  PAGES = {355--361},
  URL = {http://acl.ldc.upenn.edu/C/C00/C00-1052.pdf}
}

@ARTICLE{johnson:1999:SnSLFG,
  AUTHOR = {Mark Johnson},
  EDITOR = {Mary Dalrymple},
  TITLE = {Type-driven semantic interpretation and Feature dependencies in R-LFG},
  JOURNAL = {Semantics and Syntax in Lexical Functional Grammar},
  YEAR = {1999},
  PAGES = {359--388},
  URL = {http://arxiv.org/pdf/cmp-lg/9711014}
}

@ARTICLE{journals/jolli/Johnson99,
  TITLE = {A Resource Sensitive Interpretation of Lexical
		 Functional Grammar},
  AUTHOR = {Mark Johnson},
  JOURNAL = {Journal of Logic, Language and Information},
  YEAR = {1999},
  NUMBER = {1},
  VOLUME = {8},
  PAGES = {45--81},
  URL = {http://www.cog.brown.edu:16080/~mj/papers/jolli.pdf},
  PS = {http://bllip.cs.brown.edu/papers/jolli.ps}
}

@ARTICLE{Johnson98,
  AUTHOR = {Mark Johnson},
  TITLE = {Proof Nets and the Complexity of Processing Center Embedded Constructions},
  JOURNAL = {Journal of Logic, Language and Information},
  VOLUME = {7},
  NUMBER = {4},
  YEAR = {1998},
  ISSN = {0925-8531},
  PAGES = {433--447},
  PUBLISHER = {Kluwer Academic Publishers},
  ADDRESS = {Hingham, MA, USA},
  URL = {http://www.springerlink.com/content/q36g33331v3450g7/fulltext.pdf}
}

@INPROCEEDINGS{johnson:1998:NeMLaP3,
  AUTHOR = {Mark Johnson},
  TITLE = {The Effect of Alternative Tree Representations on Tree Bank Grammars},
  BOOKTITLE = {Proceedings of the Joint Conference on New Methods in Language Processing and Computational Natural Language Learning: (NeMLaP3/CoNLL98)},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Somerset, New Jersey},
  EDITOR = {David M. W. Powers},
  PAGES = {39--48},
  YEAR = {1998},
  URL = {http://citeseer.ist.psu.edu/johnson98effect.html}
}

@ARTICLE{mj-cl98,
  AUTHOR = {Mark Johnson},
  TITLE = {PCFG Models of Linguistic Tree Representations},
  JOURNAL = {Computational Linguistics},
  VOLUME = 24,
  NUMBER = 4,
  YEAR = 1998,
  PAGES = {613-632},
  URL = {http://www.cog.brown.edu/%7Emj/papers/johnson-97.pdf},
  PS = {http://www.cog.brown.edu/%7Emj/papers/johnson-97.ps.gz}
}

@INPROCEEDINGS{conf/acl/Johnson98,
  TITLE = {Finite-state Approximation of Constraint-based
		 Grammars using Left-corner Grammar Transforms},
  AUTHOR = {Mark Johnson},
  YEAR = {1998},
  BOOKTITLE = {COLING-ACL},
  PAGES = {619--623},
  URL = {http://acl.ldc.upenn.edu/P/P98/P98-1101.pdf},
  PS = {http://bllip.cs.brown.edu/papers/mj-acl97.ps}
}

@INPROCEEDINGS{johnson:1997:LFG,
  AUTHOR = {Mark Johnson},
  TITLE = {Features as resources in R-LFG},
  BOOKTITLE = {Proceedings of the 1997 LFG Conference},
  YEAR = {1997},
  PS = {http://csli-publications.stanford.edu/LFG2/johnson-lfg97.ps}
}

@ARTICLE{johnson1996rsl,
  TITLE = {{Resource-sensitivity in Lexical-Functional Grammar}},
  AUTHOR = {Johnson, Mark},
  JOURNAL = {Proceedings of the 1996 Roma Workshop},
  YEAR = {1996}
}

@ARTICLE{johnson:1995:CL,
  AUTHOR = {Mark Johnson},
  TITLE = {Memorization in Top-Down Parsing},
  JOURNAL = {Computational Linguistics},
  VOLUME = {21},
  NUMBER = {3},
  YEAR = {1995},
  PAGES = {405--415},
  URL = {http://acl.ldc.upenn.edu/J/J95/J95-3005.pdf}
}

@INPROCEEDINGS{johnson-bayer:1995:ESSLLI,
  AUTHOR = {Mark Johnson and Sam Bayer},
  TITLE = {Features and Agreement in Lambek Categorial Grammar},
  BOOKTITLE = {Proceedings of the 1995 ESSLLI Formal Grammar Workshop},
  YEAR = 1995,
  PAGES = {123--137},
  PS = {ftp://lx.cog.brown.edu/pub/mj/barcelona.ps.Z}
}

@INPROCEEDINGS{johnson-dorre:1995:ACL,
  AUTHOR = {Mark Johnson and Jochen Dorre},
  TITLE = {Memoization of coroutined constraints},
  BOOKTITLE = {Proceedings of the 33rd annual meeting on Association for Computational Linguistics},
  YEAR = {1995},
  PAGES = {100--107},
  LOCATION = {Cambridge, Massachusetts},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Morristown, NJ, USA},
  URL = {http://acl.ldc.upenn.edu/P/P95/P95-1014.pdf}
}

@ARTICLE{journals/coling/Johnson94,
  TITLE = {Computing with Features as Formulae},
  AUTHOR = {Mark Johnson},
  JOURNAL = {Computational Linguistics},
  YEAR = {1994},
  NUMBER = {1},
  VOLUME = {20},
  PAGES = {1--25},
  URL = {http://acl.ldc.upenn.edu/J/J94/J94-1001.pdf}
}

@INPROCEEDINGS{johnson-geman-canon-chi-riezler:1999:ACL,
  AUTHOR = {Mark Johnson and Stuart Geman and Stephen Canon and Zhiyi Chi and Stefan Riezler},
  TITLE = {Estimators for Stochastic "Unification-Based" Grammars},
  BOOKTITLE = {37th Annual Meeting of the Association for Computational Linguistics (ACL-99)},
  YEAR = 1999,
  PAGES = {535--541},
  PDF = {http://acl.ldc.upenn.edu/P/P99/P99-1069.pdf}
}

@INPROCEEDINGS{johnson-riezler:2000:NACL,
  AUTHOR = {Mark Johnson and Stefan Riezler},
  TITLE = {Exploiting auxiliary distributions in stochastic unification-based grammars},
  BOOKTITLE = {1st Meeting of the North American Chapter of the Association for Computational Linguistics (NACL-00)},
  YEAR = 2000,
  PAGES = {154--161},
  PDF = {http://acl.ldc.upenn.edu/A/A00/A00-2021.pdf}
}

@INPROCEEDINGS{kahn-EtAl:2005:HLTEMNLP,
  AUTHOR = {Kahn, Jeremy G.  and  Lease, Matthew  and  Charniak, Eugene  and  Johnson, Mark  and  Ostendorf, Mari},
  TITLE = {Effective Use of Prosody in Parsing Conversational Speech},
  BOOKTITLE = {Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (EMNLP'05)},
  MONTH = {October},
  YEAR = {2005},
  ADDRESS = {Vancouver, British Columbia, Canada},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {233--240},
  URL = {http://www.aclweb.org/anthology-new/H/H05/H05-1030}
}

@INPROCEEDINGS{kaplan-EtAl:2004:HLTNAACL,
  AUTHOR = {Kaplan, Ron  and  Riezler, Stefan  and  King, Tracy H  and  Maxwell III, John T  and  Vasserman, Alex  and  Crouch, 
Richard},
  TITLE = {Speed and Accuracy in Shallow and Deep Stochastic Parsing},
  BOOKTITLE = {HLT-NAACL 2004: Main Proceedings },
  EDITOR = {Susan Dumais, Daniel Marcu and Salim Roukos},
  YEAR = 2004,
  MONTH = {May 2 - May 7},
  ADDRESS = {Boston, Massachusetts, USA},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {97--104},
  PDF = {http://acl.ldc.upenn.edu/hlt-naacl2004/main/pdf/142_Paper.pdf},
  PS = {http://acl.ldc.upenn.edu/hlt-naacl2004/main/ps/142_Paper.ps}
}

@INPROCEEDINGS{Lease09-trec,
  AUTHOR = {Matthew Lease},
  TITLE = {{Incorporating Relevance and Psuedo-relevance Feedback in the Markov Random Field Model: Brown at the TREC'08 Relevance 
Feedback Track}},
  BOOKTITLE = {Proceedings of the 17th Text Retrieval Conference (TREC'08)},
  YEAR = 2008,
  NOTE = {Best results in track. This paper supersedes an earlier version appearing in conference's Working Notes.},
  URL = {http://bllip.cs.brown.edu/papers/lease-trec08-proc.pdf},
  ABSTRACT = {We present a new document retrieval approach combining relevance feedback, pseudo-relevance feedback, and Markov random field modeling 
of term interaction. Overall effectiveness of our combined model and the relative contribution from each component is evaluated on the 
GOV2 webpage collection. Given 0-5 feedback documents, we find each component contributes unique value to the overall ensemble, 
achieving significant improvement individually and in combination. Comparative evaluation in the 2008 TREC Relevance Feedback track 
further shows our complete system typically performs as well or better than peer systems.}
}

@CONFERENCE{Lease09-sigir,
  TITLE = {{An Improved Markov Random Field Model for Supporting Verbose Queries}},
  AUTHOR = {Matthew Lease},
  BOOKTITLE = {Proceedings of the 32nd Annual ACM SIGIR Conference},
  YEAR = 2009,
  ABSTRACT = {Recent work in supervised learning of term-based retrieval models has shown that significantly improved accuracy  can often be achieved in 
practice via better model estimation. In this paper, we show retrieval accuracy with the 
Markov random field (MRF) approach can be similarly improved via supervised estimation.  While the original MRF method 
estimates a parameter for each feature class from data, parameters within each class are set using the same fixed weighting scheme as the 
standard unigram. Because this scheme does not model context-sensitivity, its use particularly limits  retrieval accuracy with verbose 
queries. By employing supervised estimation instead, this deficit can be remedied. Retrieval experiments with verbose queries on three TREC 
document collections show our improved MRF consistently out-performs both the original MRF and the supervised unigram model. Additional 
experiments using blind-feedback and evaluation with optimal weighting demonstrate both the immediate value and further potential of more 
accurate MRF model estimation.},
  NOTE = {16% acceptance rate, to appear.}
}

@CONFERENCE{Lease09-ecir,
  TITLE = {{Regression Rank: Learning to Meet the Opportunity of Descriptive Queries}},
  AUTHOR = {Matthew Lease and James Allan and W. Bruce Croft},
  BOOKTITLE = {Proceedings of the 31st European Conference on Information Retrieval (ECIR)},
  YEAR = {2009},
  PAGES = {90--101},
  URL = {http://bllip.cs.brown.edu/papers/lease-ecir09.pdf},
  ABSTRACT = {We present a new learning to rank framework for estimating context-sensitive term weights without use of feedback. Specifically, 
knowledge of effective term weights on past queries is used to estimate term weights for new queries. This generalization is achieved by 
introducing secondary features correlated with term weights and applying regression to predict term weights given features. To improve 
support for more focused retrieval like question answering, we conduct document retrieval experiments with TREC description queries on 
three document collections. Results show significantly improved retrieval accuracy.},
  NOTE = {22% acceptance rate.}
}

@INPROCEEDINGS{Lease07-clef-proceedings,
  AUTHOR = {Matthew Lease and Eugene Charniak},
  TITLE = {A Dirichlet-smoothed Bigram Model for Retrieving Spontaneous Speech},
  BOOKTITLE = {Advances in Multilingual and Multimodal Information Retrieval: 8th Workshop of the Cross-Language Evaluation Forum, CLEF 2007, Revised Selected Papers},
  YEAR = 2008,
  ISBN = {978-3-540-85759-4},
  PUBLISHER = {Springer-Verlag},
  SERIES = {Lecture Notes in Computer Science},
  VOLUME = 5152,
  URL = {http://bllip.cs.brown.edu/papers/mlease-clef2007.pdf}
}

@INPROCEEDINGS{Lease07-clef,
  AUTHOR = {Matthew Lease and Eugene Charniak},
  TITLE = {Brown at {CL-SR}'07: Retrieving Conversational Speech in {E}nglish and {C}zech},
  BOOKTITLE = {Working Notes of the Cross-Language Evaluation Forum (CLEF): Cross-Language Speech Retrieval (CL-SR) track},
  YEAR = 2007,
  NOTE = {Corrected version},
  URL = {http://bllip.cs.brown.edu/papers/leaseCLEF2007-corrected.pdf}
}

@INPROCEEDINGS{Lease07-pikm,
  AUTHOR = {Matthew Lease},
  TITLE = {Natural Language Processing for Information Retrieval: the time is ripe (again)},
  BOOKTITLE = {Proceedings of the 1st Ph.D. Workshop at the ACM Conference on Information and Knowledge Management (PIKM)},
  YEAR = 2007,
  NOTE = {Best Paper award},
  URL = {http://bllip.cs.brown.edu/papers/lease-pikm07.pdf},
  ABSTRACT = {Paraphrasing van Rijsbergen, the time is ripe for another attempt at using natural language processing (NLP) for 
information retrieval (IR). This paper introduces my dissertation study, which will explore methods for integrating modern NLP with 
state-of-the-art IR techniques. In addition to text, I will also apply retrieval to conversational speech data, which poses a unique set of 
considerations in comparison to text. Greater use of NLP has potential to improve both text and speech retrieval.}
}

@ARTICLE{Lease06-sap,
  AUTHOR = {Lease, Matthew and Johnson, Mark and Charniak, Eugene},
  TITLE = {Recognizing disfluencies in conversational speech},
  JOURNAL = {IEEE Transactions on  Audio, Speech and Language Processing},
  VOLUME = 14,
  NUMBER = 5,
  MONTH = {September},
  YEAR = 2006,
  PAGES = {1566-1573},
  URL = {http://bllip.cs.brown.edu/papers/lease06-sap.pdf},
  ABSTRACT = {We present a system for modeling disfluency in conversational speech: repairs, fillers, and self-interruption points (IPs). For each sentence, candidate repair analyses are generated by a stochastic tree adjoining grammar (TAG) noisy-channel model. A probabilistic syntactic language model scores the fluency of each analysis, and a maximum-entropy model selects the most likely analysis given the language model score and other features. Fillers are detected independently via a small set of deterministic rules, and IPs are detected by combining the output of repair and filler detection modules. In the recent Rich Transcription Fall 2004 (RT-04F) blind evaluation, systems competed to detect these three forms of disfluency under two input conditions: a best-case scenario of manually transcribed words and a fully automatic case of automatic speech recognition (ASR) output. For all three tasks and on both types of input, our system was the top performer in the evaluation.},
  KEYWORDS = {"Disfluency modeling", "natural language processing", "rich transcription", "speech processing"}
}

@INPROCEEDINGS{Lease06aaai,
  AUTHOR = {Matthew Lease and Eugene Charniak and Mark Johnson and David McClosky},
  TITLE = {A Look At Parsing and Its Applications},
  BOOKTITLE = {Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI-06)},
  MONTH = {16--20 July},
  YEAR = {2006},
  PDF = {http://www.cs.brown.edu/people/mlease/aaai06.pdf}
}

@TECHREPORT{Lease05-tr,
  TITLE = {Parsing and Disfluency Modeling},
  AUTHOR = {Matthew Lease},
  INSTITUTION = {Brown University Department of Computer Science},
  NUMBER = {CS-05-15},
  YEAR = 2005,
  TECHREPORT = {http://www.cs.brown.edu/research/pubs/techreports/reports/CS-05-15.html}
}

@INPROCEEDINGS{Lease05-icassp,
  AUTHOR = {Matthew Lease and Eugene Charniak and Mark Johnson},
  TITLE = {Parsing and its applications for conversational speech},
  BOOKTITLE = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'05)},
  MONTH = {March 18 - March 23},
  YEAR = {2005},
  VOLUME = 5,
  PAGES = {961--964},
  URL = {http://bllip.cs.brown.edu/papers/lease05-icassp.pdf},
  ABSTRACT = {This paper provides an introduction to recent work in statistical parsing and its applications for conversational speech, with particular emphasis on the relationship between parsing and detecting speech repairs. While historically parsing and repair detection have been studied independently, we present a line of research which has spanned the boundary between the two and demonstrated the efficacy of this synergistic approach. Our presentation highlights successes to date, remaining challenges, and promising future work.}
}

@INPROCEEDINGS{Lease05-ijcnlp,
  AUTHOR = {Lease, Matthew and Charniak, Eugene},
  TITLE = {Parsing Biomedical Literature},
  BOOKTITLE = {Proceedings of the 2nd International Joint Conference on Natural Language Processing (IJCNLP'05)},
  EDITOR = {R. Dale and K.-F. Wong and J. Su and O. Kwong},
  MONTH = {October 11 - October 13},
  ADDRESS = {Jeju Island, Korea},
  YEAR = {2005},
  PAGES = {58 -- 69},
  PUBLISHER = {Springer-Verlag},
  SERIES = {Lecture Notes in Computer Science},
  VOLUME = 3651,
  URL = {http://bllip.cs.brown.edu/papers/lease-ijcnlp05.pdf},
  ABSTRACT = {We present a preliminary study of several parser adaptation techniques evaluated on the GENIA corpus of MEDLINE abstracts [1,2]. We begin by observing that the Penn Treebank (PTB) is lexically impoverished when measured on various genres of scientific and technical writing, and that this significantly impacts parse accuracy. To resolve this without requiring in-domain treebank data, we show how existing domain-specific lexical resources may be leveraged to augment PTB-training: part-of-speech tags, dictionary collocations, and named-entities. Using a state-of-the-art statistical parser [3] as our baseline, our lexically-adapted parser achieves a 14.2\% reduction in error. With oracle-knowledge of named-entities, this error reduction improves to 21.2\%.}
}

@INPROCEEDINGS{lease-johnson:2006:HLT-NAACL06-Short,
  AUTHOR = {Lease, Matthew  and  Johnson, Mark},
  TITLE = {Early Deletion of Fillers In Processing Conversational Speech},
  BOOKTITLE = {Proceedings of the Human Language Technology Conference of the NAACL (HLT-NAACL'06), Companion Volume: Short Papers},
  MONTH = {June},
  YEAR = {2006},
  ADDRESS = {New York City, USA},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {73--76},
  URL = {../papers/mlease_naacl06.pdf},
  NOTE = {Version here corrects Table 2 in published version.}
}

@MASTERSTHESIS{Lian05,
  AUTHOR = {Heng Lian},
  TITLE = {Chinese Language Parsing with Maximum-Entropy-Inspired Parser},
  YEAR = 2005,
  SCHOOL = {Brown University},
  ADDRESS = {Providence, RI},
  PDF = {http://bllip.cs.brown.edu/papers/lian_thesis.pdf},
  ABSTRACT = {The Chinese language has many special characteristics that make parsing difficult.
The performance of state-of-the-art parser is much worse than that for the English
language, with an f-score about 10\% below that of English. We present the result
of a maximum-entropy-inspired parser [3] on Penn Chinese TreeBank 1.0 and 4.0,
achieving precision/recall of 78.6/75.6 on CTB1.0 and 79.1/75.0 on CTB 4.0. We
also apply the MaxEnt reranker [4] on the 50 best parses and get about 6\% error
reduction. The parser is also applied directly to unsegmented sentences and also
achieves state-of-the-art performance.}
}

@INPROCEEDINGS{mason-charniak:2011,
  AUTHOR = {Mason, Rebecca and Charniak, Eugene},
  TITLE = {Extractive Multi-Document Summaries Should Explicitly Not Contain Document-Specific Content},
  BOOKTITLE = {Proceedings of the ACL 2011 Workshop on Automatic Summarization for Different Genres, Media, and Languages},
  ADDRESS = {Portland, Oregon},
  YEAR = {2011},
  PUBLISHER = {Association for Computational Linguistics},
  URL = {http://cs.brown.edu/people/rebecca/8_Paper.pdf}
}

@INPROCEEDINGS{mason-charniak:2011:TAC,
  AUTHOR = {Mason, Rebecca and Charniak, Eugene},
  TITLE = {BLLIP at TAC 2011: A General Summarization System for a Guided Summarization Task},
  BOOKTITLE = {Proceedings of TAC 2011},
  YEAR = 2011,
  URL = {http://cs.brown.edu/people/rebecca/tac_writeup.pdf}
}

@INPROCEEDINGS{mason-charniak:2012:NAACL,
  AUTHOR = {Mason, Rebecca and Charniak, Eugene},
  TITLE = {Apples to Oranges: Evaluating Image Annotations from Natural Language Processing Systems},
  BOOKTITLE = {NAACL-2012: Main Proceedings},
  ADDRESS = {Montreal, Canada},
  YEAR = {2012},
  PUBLISHER = {Association for Computational Linguistics},
  URL = {http://cs.brown.edu/people/rebecca/rmason_naacl2012.pdf}
}

@INPROCEEDINGS{mason:2013:SRW,
  AUTHOR = {Mason, Rebecca},
  TITLE = {Domain-Independent Captioning of Domain-Specific Images},
  BOOKTITLE = {Proceedings of the 2013 NAACL HLT Student Research Workshop},
  MONTH = {June},
  YEAR = {2013},
  ADDRESS = {Atlanta, Georgia},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {69--76},
  URL = {http://www.aclweb.org/anthology/N13-2010}
}

@INPROCEEDINGS{mason:2013:WVL,
  AUTHOR = {Mason, Rebecca and Charniak, Eugene},
  TITLE = {Annotation of Online Shopping Images without Labeled Training Examples},
  BOOKTITLE = {Proceedings of Workshop on Vision and Language},
  MONTH = {June},
  YEAR = {2013},
  ADDRESS = {Atlanta, Georgia},
  PUBLISHER = {Association for Computational Linguistics},
  URL = {http://cs.brown.edu/people/rebecca/wvl.pdf}
}

@INPROCEEDINGS{mason-charniak:2014:W14-16,
  AUTHOR = {Mason, Rebecca  and  Charniak, Eugene},
  TITLE = {Domain-Specific Image Captioning},
  BOOKTITLE = {Proceedings of the Eighteenth Conference on Computational Natural Language Learning},
  MONTH = {June},
  YEAR = {2014},
  ADDRESS = {Ann Arbor, Michigan},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {11--20},
  URL = {http://www.aclweb.org/anthology/W14-1602}
}

@INPROCEEDINGS{mason-charniak:2014:P14-2,
  AUTHOR = {Mason, Rebecca  and  Charniak, Eugene},
  TITLE = {Nonparametric Method for Data-driven Image Captioning},
  BOOKTITLE = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  MONTH = {June},
  YEAR = {2014},
  ADDRESS = {Baltimore, Maryland},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {592--598},
  URL = {http://www.aclweb.org/anthology/P14-2097}
}

@INPROCEEDINGS{choe-charniak:2013:EMNLP,
  AUTHOR = {Choe, Do Kook  and  Charniak, Eugene},
  TITLE = {Naive {Bayes} Word Sense Induction},
  BOOKTITLE = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing},
  MONTH = {October},
  YEAR = {2013},
  ADDRESS = {Seattle, Washington, USA},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {1433--1437},
  URL = {http://www.aclweb.org/anthology/D13-1148}
}

@INPROCEEDINGS{wallace-EtAl:2014:P14-2,
  AUTHOR = {Wallace, Byron C.  and  Choe, Do Kook  and  Kertz, Laura  and  Charniak, Eugene},
  TITLE = {Humans Require Context to Infer Ironic Intent (so Computers Probably do, too)},
  BOOKTITLE = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  MONTH = {June},
  YEAR = {2014},
  ADDRESS = {Baltimore, Maryland},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {512--516},
  URL = {http://www.aclweb.org/anthology/P14-2084}
}

@INPROCEEDINGS{wallace-choe-charniak:2015:ACL-IJCNLP,
  AUTHOR = {Wallace, Byron C.  and  Choe, Do Kook  and  Charniak, Eugene},
  TITLE = {Sparse, Contextually Informed Models for Irony Detection: Exploiting User Communities, Entities and Sentiment},
  BOOKTITLE = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  MONTH = {July},
  YEAR = {2015},
  ADDRESS = {Beijing, China},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {1035--1044},
  URL = {http://www.aclweb.org/anthology/P15-1100}
}

@INPROCEEDINGS{choe-mcclosky:2015:ACL-IJCNLP,
  AUTHOR = {Choe, Do Kook  and  McClosky, David},
  TITLE = {Parsing Paraphrases with Joint Inference},
  BOOKTITLE = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  MONTH = {July},
  YEAR = {2015},
  ADDRESS = {Beijing, China},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {1223--1233},
  URL = {http://www.aclweb.org/anthology/P15-1118}
}

@INPROCEEDINGS{choe-mcclosky-charniak:2015:EMNLP,
  AUTHOR = {Choe, Do Kook  and  McClosky, David  and  Charniak, Eugene},
  TITLE = {Syntactic Parse Fusion},
  BOOKTITLE = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing},
  MONTH = {September},
  YEAR = {2015},
  ADDRESS = {Lisbon, Portugal},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {1360--1366},
  URL = {http://aclweb.org/anthology/D15-1160}
}

@INPROCEEDINGS{tanner-charniak:2015:NAACL-HLT,
  AUTHOR = {Tanner, Chris  and  Charniak, Eugene},
  TITLE = {A Hybrid Generative/Discriminative Approach To Citation Prediction},
  BOOKTITLE = {Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  MONTH = {May--June},
  YEAR = {2015},
  ADDRESS = {Denver, Colorado},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {75--83},
  URL = {http://www.aclweb.org/anthology/N15-1008}
}

@INPROCEEDINGS{mcclosky-charniak-johnson:2006:COLACL,
  AUTHOR = {McClosky, David  and  Charniak, Eugene  and  Johnson, Mark},
  TITLE = {Reranking and Self-Training for Parser Adaptation},
  BOOKTITLE = {Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for 
Computational Linguistics (ACL'06)},
  MONTH = {July},
  YEAR = {2006},
  ADDRESS = {Sydney, Australia},
  PAGES = {337--344},
  PUBLISHER = {Association for Computational Linguistics},
  URL = {http://www.aclweb.org/anthology/P/P06/P06-1043},
  PS = {http://cs.brown.edu/~dmcc/papers/dmcc-acl-2006.ps}
}

@INPROCEEDINGS{mcclosky-charniak-johnson:2006:HLT-NAACL06-Main,
  AUTHOR = {McClosky, David  and  Charniak, Eugene  and  Johnson, Mark},
  TITLE = {Effective Self-Training for Parsing},
  BOOKTITLE = {Proceedings of the Human Language Technology Conference of the NAACL, Main Conference},
  MONTH = {June},
  YEAR = {2006},
  ADDRESS = {New York City, USA},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {152--159},
  URL = {http://www.aclweb.org/anthology/N/N06/N06-1020},
  PS = {http://cs.brown.edu/~dmcc/papers/dmcc-naacl-2006.ps},
  SLIDES = {http://cs.brown.edu/~dmcc/papers/dmcc-naacl-2006-slides.pdf}
}

@INPROCEEDINGS{mcclosky-charniak:2008:ACLShort,
  AUTHOR = {McClosky, David  and  Charniak, Eugene},
  TITLE = {Self-Training for Biomedical Parsing},
  BOOKTITLE = {Proceedings of ACL-08: HLT, Short Papers},
  MONTH = {June},
  YEAR = {2008},
  ADDRESS = {Columbus, Ohio},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {101--104},
  URL = {http://www.aclweb.org/anthology/P/P08/P08-2026}
}

@INPROCEEDINGS{mcclosky-charniak-johnson:2008:COLING,
  AUTHOR = {McClosky, David  and  Charniak, Eugene  and  Johnson, Mark},
  TITLE = {When is Self-training Effective for Parsing?},
  BOOKTITLE = {Proceedings of the 22nd International Conference on Computational Linguistics (COLING'08)},
  MONTH = {August},
  YEAR = {2008},
  ADDRESS = {Manchester, UK},
  URL = {http://cs.brown.edu/~dmcc/papers/dmcc-coling-2008.pdf},
  PS = {http://cs.brown.edu/~dmcc/papers/dmcc-coling-2008.ps}
}

@TECHREPORT{mcclosky-tr08,
  AUTHOR = {David McClosky},
  TITLE = {Modeling Valence Effects in Unsupervised Grammar Induction},
  NUMBER = {CS-09-01},
  YEAR = {2008},
  INSTITUTION = {Brown University},
  ADDRESS = {Providence, RI, USA},
  TECHREPORT = {http://www.cs.brown.edu/research/pubs/techreports/reports/CS-09-01.html},
  ABSTRACT = {We extend the dependency grammar induction model of Klein and Manning (2004) to incorporate further valence information. Our extensions achieve significant improvements in the task of unsupervised dependency grammar induction.  We use an expanded grammar which tracks higher orders of valence and allows each valence slot to be filled by a separate distribution rather than using one distribution for all slots.  Additionally, we show that our performance improves if our grammar restricts the maximum number of attachments in each direction, forcing our system to focus on the common case.  Taken together, these techniques constitute a 23.4\% error reduction in dependency grammar induction over the model by Klein and Manning (2004) on English.}
}

@INPROCEEDINGS{McClosky:2010:ADA:1857999.1858003,
  AUTHOR = {McClosky, David and Charniak, Eugene and Johnson, Mark},
  TITLE = {Automatic domain adaptation for parsing},
  BOOKTITLE = {Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics},
  SERIES = {HLT '10},
  YEAR = {2010},
  ISBN = {1-932432-65-5},
  LOCATION = {Los Angeles, California},
  PAGES = {28--36},
  NUMPAGES = {9},
  URL = {http://dl.acm.org/citation.cfm?id=1857999.1858003},
  ACMID = {1858003},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Stroudsburg, PA, USA}
}

@INPROCEEDINGS{miller00,
  AUTHOR = {Scott Miller and Heidi Fox and Lance Ramshaw and Ralph Weischedel},
  TITLE = {A novel use of statistical parsing to extract information from text},
  BOOKTITLE = {Proceedings of the first conference on North American chapter of the Association for Computational Linguistics (NAACL'00)},
  YEAR = {2000},
  PAGES = {226--233},
  LOCATION = {Seattle, Washington},
  PUBLISHER = {Morgan Kaufmann Publishers Inc.},
  ADDRESS = {San Francisco, CA, USA},
  URL = {http://acl.ldc.upenn.edu/A/A00/A00-2030.pdf}
}

@INPROCEEDINGS{riezler-etal-acl00,
  AUTHOR = {Stefan Riezler and Detlef Prescher and Jonas Kuhn and Mark Johnson},
  TITLE = {Lexicalized Stochastic Modeling of Constraint-Based Grammars using Log-Linear Measures and EM Training},
  BOOKTITLE = {In Proceedings of 38th Annual Meeting of the Association for Compuational Linguistics (ACL-00)},
  YEAR = {2000},
  URL = {http://arxiv.org/abs/cs.CL/0008034}
}

@INPROCEEDINGS{riezler-EtAl:2002:ACL,
  AUTHOR = {Stefan Riezler and Tracy H. King and Ronald M. Kaplan and Richard Crouch and John T. III Maxwell and Mark Johnson},
  TITLE = {Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques},
  BOOKTITLE = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL-02)},
  YEAR = 2002,
  PAGES = {271-278},
  PDF = {http://acl.ldc.upenn.edu/P/P02/P02-1035.pdf}
}

@INPROCEEDINGS{Roark06-icassp,
  AUTHOR = {Roark, B. and Yang Liu and Harper, M. and Stewart, R. and Lease, M. and Snover, M. and Shafran, I. and Dorr, B. and Hale, J. and Krasnyanskaya, A. and Yung, L.},
  TITLE = {Reranking for Sentence Boundary Detection in Conversational Speech},
  BOOKTITLE = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'06)},
  YEAR = 2006,
  MONTH = {May 14--19},
  PAGES = {545--548},
  URL = {http://bllip.cs.brown.edu/papers/roark06-icassp.pdf},
  ABSTRACT = {We present a reranking approach to sentence-like unit (SU) boundary detection, one of the EARS metadata extraction tasks. Techniques for generating relatively small n-best lists with high oracle accuracy are presented. For each candidate, features are derived from a range of information sources, including the output of a number of parsers. Our approach yields significant improvements over the best performing system from the NIST RT-04F community evaluation.}
}

@INPROCEEDINGS{Roark06-lrec,
  AUTHOR = {Brian Roark and Mary Harper and Eugene Charniak and Bonnie Dorr and Mark Johnson and Jeremy G. Kahn and Yang Liu and Mari Ostendorf and John Hale and Anna Krasnyanskaya and Matthew Lease and Izhak Shafran and Matthew Snover and Robin Stewart and Lisa Yung},
  TITLE = {SParseval: Evaluation Metrics for Parsing Speech},
  BOOKTITLE = {Fifth International Conference on Language Resources and Evaluation (LREC'06)},
  YEAR = 2006,
  ADDRESS = {Genoa, Italy},
  PDF = {http://www.cslu.ogi.edu/people/roark/lrec2006.sparseval.pdf}
}

@INPROCEEDINGS{DBLP:conf/acl/RoarkSCJ04,
  AUTHOR = {Brian Roark and
               Murat Saraclar and
               Michael Collins and
               Mark Johnson},
  TITLE = {Discriminative Language Modeling with Conditional Random
               Fields and the Perceptron Algorithm.},
  BOOKTITLE = {ACL},
  YEAR = {2004},
  PAGES = {47-54},
  EE = {http://acl.ldc.upenn.edu/acl2004/main/pdf/320_pdf_2-col.pdf},
  BIBSOURCE = {DBLP, http://dblp.uni-trier.de}
}

@ARTICLE{Roark01,
  AUTHOR = {Brian Roark},
  TITLE = {Probabilistic top-down parsing and language modeling},
  JOURNAL = {Computational Linguistics},
  YEAR = 2001,
  VOLUME = 27,
  NUMBER = 2,
  PAGES = {249-276},
  URL = {http://acl.ldc.upenn.edu/J/J01/J01-2004.pdf}
}

@INPROCEEDINGS{Roark00,
  AUTHOR = {Brian Roark and
               Eugene Charniak},
  TITLE = {Measuring efficiency in high-accuracy, broad-coverage statistical
               parsing},
  BOOKTITLE = {Proceedings of the COLING'00 Workshop on Efficiency in Large-scale Parsing Systems},
  PAGES = {29-36},
  YEAR = {2000},
  URL = {http://arxiv.org/abs/cs.CL/0008027}
}

@INPROCEEDINGS{Roark-Johnson:1999:ACL,
  AUTHOR = {Brian Roark and Mark Johnson},
  TITLE = {Efficient probabilistic top-down and left-corner parsing},
  BOOKTITLE = {Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics (ACL '99)},
  YEAR = {1999},
  PAGES = {421--428},
  URL = {http://acl.ldc.upenn.edu/P/P99/P99-1054.pdf}
}

@INPROCEEDINGS{swanson-charniak:2014:EACL2014-SP,
  AUTHOR = {Swanson, Ben  and  Charniak, Eugene},
  TITLE = {Data Driven Language Transfer Hypotheses},
  BOOKTITLE = {Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers},
  MONTH = {April},
  YEAR = {2014},
  ADDRESS = {Gothenburg, Sweden},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {169--173},
  URL = {http://www.aclweb.org/anthology/E14-4033}
}

@INPROCEEDINGS{swanson-charniak:2013:NAACL-HLT,
  AUTHOR = {Swanson, Ben  and  Charniak, Eugene},
  TITLE = {Extracting the Native Language Signal for Second Language Acquisition},
  BOOKTITLE = {Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  MONTH = {June},
  YEAR = {2013},
  ADDRESS = {Atlanta, Georgia},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {85--94},
  URL = {http://www.aclweb.org/anthology/N13-1009}
}

@INPROCEEDINGS{swanson-EtAl:2013:ACL2013,
  AUTHOR = {Swanson, Ben  and  Yamangil, Elif  and  Charniak, Eugene  and  Shieber, Stuart},
  TITLE = {A Context Free TAG Variant},
  BOOKTITLE = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  MONTH = {August},
  YEAR = {2013},
  ADDRESS = {Sofia, Bulgaria},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {302--310},
  URL = {http://www.aclweb.org/anthology/P13-1030}
}

@INPROCEEDINGS{Swanson:2012:NLD:2390665.2390713,
  AUTHOR = {Swanson, Ben and Charniak, Eugene},
  TITLE = {Native language detection with tree substitution grammars},
  BOOKTITLE = {Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers - Volume 2},
  SERIES = {ACL '12},
  YEAR = {2012},
  LOCATION = {Jeju Island, Korea},
  PAGES = {193--197},
  NUMPAGES = {5},
  URL = {http://dl.acm.org/citation.cfm?id=2390665.2390713},
  ACMID = {2390713},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Stroudsburg, PA, USA}
}

@INPROCEEDINGS{Swanson:2012:CDE:2382029.2382077,
  AUTHOR = {Swanson, Ben and Yamangil, Elif},
  TITLE = {Correction detection and error type selection as an ESL educational aid},
  BOOKTITLE = {Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  SERIES = {NAACL HLT '12},
  YEAR = {2012},
  ISBN = {978-1-937284-20-6},
  LOCATION = {Montreal, Canada},
  PAGES = {357--361},
  NUMPAGES = {5},
  URL = {http://dl.acm.org/citation.cfm?id=2382029.2382077},
  ACMID = {2382077},
  PUBLISHER = {Association for Computational Linguistics},
  ADDRESS = {Stroudsburg, PA, USA}
}

@INPROCEEDINGS{turner-charniak:2005:ACL,
  AUTHOR = {Turner, Jenine  and  Charniak, Eugene},
  TITLE = {Supervised and Unsupervised Learning for Sentence Compression},
  BOOKTITLE = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05)},
  MONTH = {June},
  YEAR = {2005},
  ADDRESS = {Ann Arbor, Michigan},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {290--297},
  URL = {http://www.aclweb.org/anthology/P/P05/P05-1036}
}

@INPROCEEDINGS{turner-charniak:2007:ShortPapers,
  AUTHOR = {Turner, Jenine  and  Charniak, Eugene},
  TITLE = {Language Modeling for Determiner Selection},
  BOOKTITLE = {Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers},
  MONTH = {April},
  YEAR = {2007},
  ADDRESS = {Rochester, New York},
  PUBLISHER = {Association for Computational Linguistics},
  PAGES = {177--180},
  URL = {http://www.aclweb.org/anthology/N/N07/N07-2045}
}


This file has been generated by bibtex2html 1.83.