Coling 2008

Manchester, 18-22 August, 2008

The 22nd International Conference on Computational Linguistics
Home · Programme · Info for authors · Workshops · Tutorials · Registration · Venue · Accommodation · Sponsorship · Archive · ICCL

Programme

Invited speakers ·Papers ·Posters ·Demos

From a total of 612 submissions including full papers, posters and demos, we have accepted:

Invited speakers

We are pleased to confirm the invited keynote speakers, as follows:

Dr Elizabeth Shriberg, Senior Research Psycholinguist
Speech Technology & Research Laboratory, SRI International, Menlo Park CA
and International Computer Science Institute, Berkeley CA
Prof John Shawe-Taylor, Director
Centre for Computational Statistics and Machine Learning
University College London

List of accepted papers

Two-phased event relation acquisition: coupling the relation-oriented and argument-oriented approachesShuya Abe, Kentaro Inui and Yuji Matsumoto
A supervised algorithm for verb disambiguation into VerbNet classesOmri Abend, Roi Reichart and Ari Rappoport
On robustness and domain adaptation using SVD for word sense disambiguationEneko Agirre and Oier Lopez de Lacalle
An improved hierarchical Bayesian model of language for document classificationBen Allison
Improving alignments for better confusion networks for combining machine translation systemsNecip Fazil Ayan, Jing Zheng and Wen Wang
Verification and implementation of language-based deception indicators in civil and criminal narrativesJoan Bachenko, Eileen Fitzpatrick and Michael Schonwetter
Enhancing multilingual latent semantic analysis with term alignment informationBrett Bader and Peter Chew
Weakly supervised supertagging with grammar-informed initializationJason Baldridge
Good neighbors make good senses: exploiting distributional similarity for unsupervised wsdSamuel Brody and Mirella Lapata
Classifying dialogue actions in tutorial dialogueMark Buckley and Magdalena Wolska
An affordance-based approach to noun-compound interpretationCristina Butnariu and Tony Veale
Comparing the benefits of WordNet's semantic similarity with simple morpho-syntactic features for the resolution of noun phrase coordination ambiguityEkaterina Buyko and Udo Hahn
Parametric: an automatic evaluation metric for paraphrasingChris Callison-Burch, Trevor Cohn and Mirella Lapata
Other-anaphora resolution in biomedical texts with automatic mined patternsBin Chen, Xiaofeng Yang, Jian Su and Chew Lim Tan
Improve SMT through hypotheses regenerationBoxing Chen, Min Zhang, Ai Ti Aw and Haizhou Li
Learning reliable information for dependency parsing adaptationWenliang Chen and Hitoshi Isahara
Latent morpho-semantic analysis: multilingual information retrieval with character n-grams and mutual informationPeter A. Chew, Brett W. Bader and Ahmed Abdelali
Sentence compression beyond word deletionTrevor Cohn and Mirella Lapata
Mind the gap: dangers of divorcing evaluations of summary content from linguistic qualityJohn Conroy and Hoa Trang Dang
Hybrid processing for grammar and style checkingBerthold Crysmann, Nuria Bertomeu, Peter Adolphs, Daniel Flickinger and Tina Klüwer
KnowNet: building a large net of knowledge from the webMontse Cuadros and German Rigau
A classifier-based approach to preposition and determiner error correction in L2 EnglishRachele De Felice and Stephen Pulman
Pedagogically useful extractive summaries for science educationSebastian de la Chica, Faisal Ahmad, James H. Martin and Tamara Sumner
Re-estimation of lexical parameters for treebank PCFGsTejaswini Deoskar
Looking for troubleStijn De Saeger, Kentaro Torisawa and Jun'ichi Kazama
Representations for category disambiguationMarkus Dickinson
Syntactic reordering integrated with phrase-based SMTJakob Elming
Efficiently parsing with the product-free Lambek calculusTimothy A. D. Fowler
A probabilistic model for measuring grammaticality and similarity of automatically generated paraphrases of predicate phrasesAtsushi Fujita and Satoshi Sato
Retrieving bilingual verb-noun collocations by integrating cross-language category hierarchiesFumiyo Fukumoto, Yoshimi Suzuki and Kazuyuki Yamashita
Mining opinions in comparative sentencesMurthy Ganapathibhotla and Bing Liu
Semantic principlesClaire Gardent
Statistical anaphora resolution in biomedical textsCaroline Gasperin
Instance-based ontology population exploiting named-entity substitutionClaudio Giuliano and Alfio Gliozzo
Measuring topic homogeneity and its application to dictionary-based word sense disambiguationAnn Gledson and John Keane
Using web-search results to measure word-group similarityAnn Gledson and John Keane
An algorithm for adverbial aspect shiftSabine Gruender
Dependency-based n-gram models for general purpose sentence realisationYuqing Guo, Josef van Genabith and Haifeng Wang
Homotopy-based semi-supervised hidden Markov models for sequence labelingGholamreza Haffari and Anoop Sarkar
Tracking the dynamic evolution of participants salience in a discussionAhmed Hassan, Anthony Fader, Michael Crespin, Kevin Quinn, Burt Monroe, Michael Colaresi and Dragomir Radev
Improving statistical machine translation using lexicalized rule selectionZhongjun He, Qun Liu and Shouxun Lin
Evaluating unsupervised part-of-speech tagging for grammar inductionWilliam Headden, David McClosky and Eugene Charniak
Using discourse commitments to recognize textual entailmentAndrew Hickl
Modeling Chinese documents with topical word-character modelsWei Hu, Nobuyuki Shimizu, Hiroshi Nakagawa and Huanye Sheng
Generation of referring expressions: managing structural ambiguitiesImtiaz Hussain Khan, Graeme Ritchie and Kees van Deemter
Non-compositional language model and pattern dictionary development for Japanese compound and complex sentencesSatoru Ikehara, Masato Tokuhisa and Jin'ichi Murakami
Japanese dependency parsing using tournament modelMasakazu Iwatate, Masayuki Asahara and Yuji Matsumoto
Contents modelling of Neo-Sumerian Ur III economic text corpusWojciech Jaworski
Generating Chinese couplets using a statistical MT approachLong Jiang and Ming Zhou
Word lattice reranking for Chinese word segmentation and part-of-speech taggingWenbin Jiang, Haitao Mi, Yajuan Lv and Qun Liu
The effect of syntactic representation on semantic role labelingRichard Johansson and Pierre Nugues
Using hidden Markov random fields to combine distribution and co-occurrence for word clusteringNobuhiro Kaji and Masaru Kitsuregawa
Textual demand analysis: detection of users’ wants and needs from opinionsHiroshi Kanayama and Tetsuya Nasukawa
A local alignment kernel in practice : a relation extraction taskSophia Katrenko and Pieter Adriaans
Coordination disambiguation without any similaritiesDaisuke Kawahara and Sadao Kurohashi
Normalizing SMS: are two metaphors better than one ?Catherine Kobus, François Yvon and Géraldine Damnati
The choice of features for classification of verbs in biomedical textsAnna Korhonen, Yuval Krymolowski and Nigel Collier
Extending a thesaurus with words from pan-Chinese sourcesOi Yee Kwong and Benjamin K. Tsou
Stopping criteria for active learning of named entity recognitionFlorian Laws and Hinrich Schütze
Reading the markets: forecasting public opinion of political candidates by news analysisKevin Lerman, Ari Gilder, Mark Dredze and Fernando Pereira
Classifying what-type questions by head noun taggingFangtao Li, Xian Zhang, Jinhui Yuan and Xiaoyan Zhu
PNR2: ranking sentences with positive and negative reinforcement for query-oriented update summarizationWenjie Li, Furu Wei, Yanxiang He and Qin Lu
Understanding and summarizing answers in community-based question answering servicesYuanjie Liu, Shasha Li, Yunbo Cao, Chin-Yew Lin, Dingyi Han and Yong Yu
Tera-scale statistical translation models via pattern matchingAdam Lopez
Authorship attribution and verification with many authors and limited dataKim Luyckx and Walter Daelemans
Modeling semantic containment and exclusion in natural language inferenceBill MacCartney and Christopher D. Manning
Linguistically-based sub-sentential alignment for terminology extraction from a bilingual automotive corpusLieve Macken, Els Lefever and Veronique Hoste
Hindi Urdu machine transliteration using finite-state transducersM G Abbas Malik, Christian Boitet and Pushpak Bhattacharyya
Comparative parser performance analysis across grammar frameworks through automatic tree conversion using synchronous grammarsTakuya Matsuzaki and Jun'ichi Tsujii
What's the date? High accuracy interpretation of weekday namesPawel Mazur and Robert Dale
When is self-training effective for parsing?David McClosky, Eugene Charniak and Mark Johnson
A unified syntactic model for parsing fluent and disfluent speechTim Miller and William Schuler
Applying discourse analysis and data mining methods to spoken OSCE assessmentsMeladel Mistica, Timothy Baldwin, Marisa Cordella and Simon Musgrave
Random restarts in minimum error rate training for statistical machine translationRobert C. Moore and Chris Quirk
Robust similarity measures for named entities matchingErwan Moreau, François Yvon and Olivier Cappé
Modeling the structure and dynamics of the consonant inventories: a complex network approachAnimesh Mukherjee, Monojit Choudhury, Anupam Basu and Niloy Ganguly
Detecting multiple facets of an event using graph-based unsupervised methodsPradeep Muthukrishnan, Joshua Gerrish and Dragomir Radev
Investigating statistical techniques for sentence-level event classificationMartina Naughton, Nicola Stokes and Joe Carthy
Feature selection for pronoun resolution towards domain adaptationNgan L.T. Nguyen
Computer aided correction and extension of a syntactic wide-coverage lexiconLionel Nicolas, Benoît Sagot, Jacques Farré, Miguel Angel Molinero Alvarez and Eric De la Clergerie
Parsing the SynTagRus treebank of RussianJoakim Nivre, Igor M. Boguslavsky and Leonid K. Iomdin
A discriminative alignment model for abbreviation recognitionNaoaki Okazaki and Jun'ichi Tsujii
Semantic classification with distributional kernelsDiarmuid Ó Séaghdha and Ann Copestake
Towards semantic role labelling for event nominalisations through bootstrapping from verbal dataSebastian Pado, Marco Pennacchiotti and Caroline Sporleder
Recent advances in a feature-rich framework for treebank annotationPetr Pajas and Jan Štepánek
A joint information model for n-best rankingPatrick Pantel and Vishnu Vyas
Scientific paper summarization using citation summary networksVahed Qazvinian and Dragomir R. Radev
Exploiting constituent dependencies for tree kernel-based semantic relation extractionLonghua Qian, Guodong Zhou, Fang Kong and Qiaoming Zhu
A method for automatic POS guessing of unknown wordsLikun Qiu, Changjian Hu and Kai Zhao
Almost flat functional semantics for speech translationManny Rayner, Pierrette Bouillon, Beth Ann Hockey and Yukie Nakao
Unsupervised induction of labeled parse trees by clustering with syntactic featuresRoi Reichart and Ari Rappoport
Anomalies in the WordNet verb hierarchyTom Richens
Translating queries into snippets for improved query expansionStefan Riezler, Yi Liu and Alexander Vasserman
Classifying chart cells for quadratic complexity context-free inferenceBrian Roark and Kristy Hollingshead
Shift-reduce dependency DAG parsingKenji Sagae and Jun'ichi Tsujii
Event frame extraction based on a gene regulation corpusYutaka Sasaki, Paul Thompson, Philip Cotter, John McNaught and Sophia Ananiadou
A fully-lexicalized probabilistic model for Japanese zero anaphora resolutionRyohei Sasano, Daisuke Kawahara and Sadao Kurohashi
Estimation of conditional probabilities with decision trees and an application to fine-grained POS taggingHelmut Schmid
Toward a psycholinguistically-motivated model of language processingWilliam Schuler, Samir AbdelRahman, Tim Miller and Lane Schwartz
Metric learning for synonym acquisitionNobuyuki Shimizu, Masato Hagiwara, Yasuhiro Ogawa, Katsuhiko Toyama and Hiroshi Nakagawa
Discourse level opinion interpretationSwapna Somasundaran, Janyce Wiebe and Josef Ruppenhofer
Acquiring sense tagged examples using relevance feedbackMark Stevenson, Yinkun Guo and Robert Gaizauskas
Topic identification for fine-grained opinion analysisVeselin Stoyanov and Claire Cardie
From word to sense: a case study of subjectivity recognitionFangzhong Su and Katja Markert
Prediction of maximal projection for semantic role labelingWeiwei Sun, Zhifang Sui and Haifeng Wang
Modeling latent-dynamics in shallow parsingXu Sun, Louis-Philippe Morency and Daisuke Okanohara
Learning entailment rules for unary templatesIdan Szpektor and Ido Dagan
Experiments with reasoning for temporal relations between eventsMarta Tatu and Munirathnam Srikanth
The ups and downs of evaluating preposition error detection in non-native English writingJoel Tetreault and Martin Chodorow
A framework for identifying textual redundancyKapil Thadani and Kathleen McKeown
Emotion classification using massive examples extracted from the webRyoko Tokuhisa, Kentaro Inui and Yuji Matsumoto
Relational-realizational parsingReut Tsarfaty
Training conditional random fields using incomplete annotationsYuta Tsuboi, Hisashi Kashima, Shinsuke Mori, Hiroki Oda and Yuji Matsumoto
A uniform approach to analogies, synonyms, antonyms, and associationsPeter Turney
Tighter integration of rule-based and statistical MT in serial system combinationNicola Ueffing, Jens Stephan, Evgeny Matusov, Loïc Dugast, George Foster, Roland Kuhn, Jean Senellart and Jin Yang
Using three way data for word sense discriminationTim Van de Cruys
Class-driven attribute extractionBenjamin Van Durme, Ting Qian and Lenhart Schubert
Source language markers in Europarl translationsHans van Halteren
A fluid knowledge representation for understanding and generating creative metaphorsTony Veale and Yanfen Hao
Using syntactic information for improving why-question answeringSuzan Verberne, Lou Boves, Nelleke Oostdijk and Peter-Arno Coppen
Coreference systems based on kernels methodsYannick Versley, Alessandro Moschitti, Massimo Poesio and Xiaofeng Yang
Collabrank: towards a collaborative approach to single-document keyphrase extractionXiaojun Wan
Investigating the portability of corpus-derived cue phrases for dialogue act classificationNick Webb and Ting Liu
Extractive summarization using supervised and semi-supervised learningKam-Fai Wong, Mingli Wu and Wenjie Li
Domain adaptation for statistical machine translation with domain dictionary and monolingual corporaHua Wu, Haifeng Wang and Chengqing Zong
Exploiting graph structure for accelerating the calculation of shortest paths in wordnetsHolger Wunsch
Linguistically annotated BTG for statistical machine translationDeyi Xiong, Min Zhang, Aiti Aw and Haizhou Li
Bayesian semi-supervised Chinese word segmentation for statistical machine translationJia Xu, Jianfeng Gao, Kristina Toutanova and Hermann Ney
Switching to real-time tasks in multi-tasking dialogueFan Yang, Peter A. Heeman and Andrew Kun
Chinese term extraction using minimal resourcesYuhang Yang, Qin Lu and Tiejun Zhao
Measuring and predicting orthographic associations: modelling the similarity of Japanese kanjiLars Yencken and Timothy Baldwin
An integrated probabilistic and logic approach to encyclopedia relation extraction with multiple featuresXiaofeng YU and Wai LAM
Chinese dependency parsing with large scale automatically constructed case structuresKun Yu, Daisuke Kawahara and Sadao Kurohashi
OntoNotes: corpus cleanup of mistaken agreement using word sense disambiguationLiang-Chih Yu, Chung-Hsien Wu and Eduard Hovy
Automatic seed word selection for unsupervised sentiment classification of Chinese textTaras Zagibalov and John Carroll
Generalized Uno and Yagiura's algorithm for alignment decompositionHao Zhang, Daniel Gildea and David Chiang
Grammar comparison study for translational equivalence modeling and statistical machine translationMin Zhang, Hongfei Jiang, Haizhou Li, Aiti Aw and Sheng Li
Sentence type based reordering model for statistical machine translationJiajun Zhang and chengqing zong
Automatic generation of parallel treebanksVentsislav Zhechev and Andy Way
A hybrid generative/discriminative framework to train a semantic parser from an un-annotated corpusDeyu Zhou and Yulan He
Diagnostic evaluation of machine translation systems using automatically constructed linguistic check-pointsMing Zhou, Bo Wang, Shujie Liu, Mu Li and Tiejun Zhao
Active learning with sampling by uncertainty and density for word sense disambiguation and text classificationJingbo Zhu, Huizhen Wang and Benjamin Tsou
Multi-criteria-based strategy to stop active learning for data annotationJingbo Zhu, Huizhen Wang and Eduard Hovy
A systematic comparison of phrase-based, hierarchical and syntax-augmented statistical mtAndreas Zollmann, Ashish Venugopal, Franz Och and Jay Ponte
To reorder or not to reorder effects of word reordering in statistical machine translationSimon Zwarts and Mark Dras

List of accepted posters

Metaphor in textual entailmentRodrigo Agerri and John Barnden
Discourse based opinion categorization: a preliminary studyNicholas Asher, Farah Benamara and Yvettes Yannick Mathieu
Towards incremental end-of-utterance detection in dialogue systemsMichaela Atterer, Timo Baumann and David Schlangen
The power of negative thinking: exploiting label disagreement in the min-cut classification frameworkMohit Bansal, Claire Cardie and Lillian Lee
Phrasal segmentation models for statistical machine translationGraeme Blackwood, Adria de Gispert and William Byrne
A scalable MMR approach to sentence scoring for multi-document update summarizationFlorian Boudin, Juan-Manuel Torres-Moreno and Marc El-Bèze
Hindi compound verbs and their automatic extractionDebasri Chakrabarti, Hemang Mandalia, Ritwik Priya, Vaijayanthi Sarma and Pushpak Bhattacharyya
Detecting erroneous uses of complex postpositions in an agglutinative languageArantza Díaz de Ilarraza, Koldo Gojenola and Maite Oronoz
Underspecified modelling of complex discourse constraintsMarkus Egg and Michaela Regneri
Construct state modification in the Arabic treebank: further analysis and improvementsRyan Gabbard and Seth Kulick
The impact of reference quality on automatic MT evaluationOlivier Hamon and Djamel Mostefa
Word sense disambiguation for all words using tree-structured conditional random fieldsJun Hatori, Yusuke Miyao and Jun'ichi Tsujii
Conceptual representation and ILP-based analysis for Chinese NPsDong Paul Ji
Scaling up analogical learningPhilippe Langlais and François Yvon
Multilingual alignments by monolingual string differencesAdrien Lardilleux and Yves Lepage
Bayes risk-based dialogue management for document retrieval system with speech interfaceTeruhisa Misu and Tatsuya Kawahara
Exact inference for multi-label classification using sparse graphical modelsYusuke Miyao and Jun'ichi Tsujii
Modeling multilinguality in ontologiesElena Montiel-Ponsoda, Guadalupe Aguado de Cea, Asunción Gómez-Pérez and Wim Peters
Quantification and implication in calendar expressions represented with finite-state transducersJyrki Niemi and Kimmo Koskenniemi
Experiments in discriminating phrase-based translations on the basis of syntactic coupling featuresVassilina Nikoulina and Marc Dymetman
Using very simple statistics for review search: an explorationBo Pang and Lillian Lee
Generation under space constraintsCecile Paris, Nathalie Colineau, Andrew Lampert and Joan Giralt Duran
A language-independent approach to keyphrase extraction and evaluationMari-Sanna Paukkeri, Ilari Nieminen, Matti Pöllä and Timo Honkela
Easily identifiable discourse relationsEmily Pitler, Mridhula Raghupathy, Hena Mehta, Ani Nenkova, Alan Lee and Aravind Joshi
Rank distance as a stylistic similarityMarius Popescu and Liviu Dinu
Integrating motion predicate classes with spatial and temporal annotationsJames Pustejovsky and Jessica Moszkowicz
Comparative evaluation of Arabic language morphological analysers and stemmersMajdi Sawalha and Eric Atwell
A complete and modestly funny system for generating and performing Japanese stand-up comedyJonas Sjobergh and Kenji Araki
On the weak generative capacity of weighted context-free grammarsAnders Søgaard
Range concatenation grammars for translationAnders Søgaard
On "redundancy" in selecting attributes for generating referring expressionsPhilipp Spanger, Takehiro Kurosawa and Takenobu Tokunaga
Construction of an infrastructure for providing users with suitable language resourcesHitomi Tohyama, Shunsuke Kozawa, Kiyotaka Uchimoto, Shigeki Matsubara and Hitoshi Isahara
Experiments in base-NP chunking and its role in dependency parsing for ThaiShisanu Tongchim, Virach Sornlertlamvanich and Hitoshi Isahara
Building a bilingual lexicon using phrase-based statistical machine translation via a pivot languageTakashi Tsunakawa, Naoaki Okazaki and Jun'ichi Tsujii
Explaining similarity of termsVishnu Vyas and Patrick Pantel
Robust and efficient Chinese word dependency analysis with linear kernel support vector machinesYu-Chieh Wu
Sentence compression as a step in summarization or an alternative path in text shorteningMehdi Yousfi-Monod and Violaine Prince

List of accepted demos

Online-monitoring security-related events Martin Atkinson, Jakub Piskorski, Bruno Pouliquen, Ralf Steinberger, Hristo Tanev and Vanni Zavarella
Semantic visualization and meaning computation Venant Fabienne
A grammar checking system for Punjabi Mandeep Gill and Gurpreet Lehal
A toolchain for grammarians Bruno Guillaume, Joseph Le Roux, Jonathan Marchand, Guy Perrier, Karën Fort and Jennifer Planul
A Punjabi to Hindi machine translation system Gurpreet Singh Josan and Gurpreet Singh Lehal
Advanced dialogue tools for automatically generating information state update dialogue systems from business user resources Oliver Lemon, Xingkun Liu and Hastie Helen
Multilingual mobile-phone translation services for world travelers Michael Paul, Hideo Okuma, Hirofumi Yamamoto, Eiichiro Sumita, Shigeki Matsuda, Tohru Shimizu and Satoshi Nakamura
Multilingual assistant for medical diagnosing and drug prescription based on category ranking Fernando Ruiz-Rico, Jose-Luis Vicedo and María-Consuelo Rubio-Sánchez
Entailment-based question answering for structured data Bogdan Sacaleanu, Christian Spurk, Constantin Orasan, Oscar Ferrandez, Milen Kouylekov, Matteo Negri and Shiyan Ou
Shahmukhi to Gurmukhi transliteration system Tejinder Singh Saini and Gurpreet Singh Lehal
A linguistic knowledge discovery tool: Very large ngram database search with arbitrary wildcards Satoshi Sekine
Temporal processing with the TARSQI toolkit Marc Verhagen and James Pustejovsky