Sponsored by:

2002 Conference on Empirical Methods in Natural Language Processing
(EMNLP 2002)

University of Pennsylvania, Philadelphia, PA, USA

July 6-7, 2002

by SIGDAT and the Association for Computational Linguistics

EMNLP'02 Home Page
Author Index

The Program

Saturday, July 6, 2002
Sat 8:30-8:40 Welcome from SIGDAT
Sat 8:40-9:05 Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms
Michael Collins
Sat 9:05-9:30 Conditional Structure versus Conditional Estimation in NLP Models
Dan Klein  and  Christopher D. Manning
Sat 9:30-9:55 An Incremental Decision List Learner
Joshua Goodman
Sat 9:55-10:25 Coffee Break
Word Sense Disambiguation
Sat 10:25-10:50 Modeling Consensus: Classifier Combination for Word Sense Disambiguation
Radu Florian  and  David Yarowsky
Sat 10:50-11:15 Augmented Mixture Models for Lexical Disambiguation
Silviu Cucerzan  and  David Yarowsky
Sat 11:15-11:40 An Empirical Evaluation of Knowledge Sources and Learning Algorithms for Word Sense Disambiguation
Yoong Keok Lee  and  Hwee Tou Ng
Sat 11:40-11:50 Short Break
Sat 11:50-12:50 Invited Talk: Learning and Inference in Natural Language
Dan Roth
Sat 12:50-2:00 Lunch break
Parsing I / Coreference
Sat 2:00-2:25 Parsing and Disfluency Placement
Donald Engel, Eugene Charniak  and  Mark Johnson
Sat 2:25-2:50 Combining Sample Selection and Error-Driven Pruning for Machine Learning of Coreference Rules
Vincent Ng  and  Claire Cardie
Sat 2:50-3:15 Transformational Priors Over Grammars
Jason Eisner
Sat 3:15-3:45 Coffee Break
Information Extraction (A) / Machine Translation I (B)
Sat 3:45-4:10 (A) Kernel Methods for Relation Extraction
Dmitry Zelenko, Chinatsu Aone  and  Anthony Richardella
Sat 4:10-4:35 (A) Thumbs up? Sentiment Classification using Machine Learning Techniques
Bo Pang, Lillian Lee  and  Shivakumar Vaithyanathan
Sat 3:45-4:10 (B) Extentions to HMM-based Statistical Word Alignment Models
Kristina Toutanova, H. Tolga Ilhan  and  Christopher Manning
Sat 4:10-4:35 (B) From Words to Corpora: Recognizing Translation
Noah A. Smith
Sat 4:35-4:45 Short Break
Parsing II (A) / Lexicons I (B)
Sat 4:45-5:10 (A) Fast LR parsing Using Rich (Tree Adjoining) Grammars
Carlos A. Prolo
Sat 5:10-5:35 (A) Handling Noisy Training and Testing Data
Don Blaheta
Sat 4:45-5:10 (B) Spectral Clustering for German Verbs
Chris Brew  and  Sabine Schulte im Walde
Sat 5:10-5:35 (B) Exploiting Strong Syntactic Heuristics and Co-Training to Learn Semantic Lexicons
William Phillips  and  Ellen Riloff
Sunday, July 7, 2002
Machine Translation II
Sun 8:40-9:05 A Phrase-Based, Joint Probability Model for Statistical Machine Translation
Daniel Marcu  and  William Wong
Sun 9:05-9:30 Minimum Bayes-Risk Word Alignments of Bilingual Texts
Shankar Kumar  and  William Byrne
Sun 9:30-9:55 User-Friendly Text Prediction For Translators
George Foster, Philippe Langlais  and  Guy Lapalme
Sun 9:55-10:25 Coffee Break
Machine Translation III (A) / Information Retrieval I (B)
Sun 10:25-10:50 (A) Generation of Word Graphs in Statistical Machine Translation
Nicola Ueffing, Franz Josef Och  and  Hermann Ney
Sun 10:50-11:15 (A) Bootstrapping Lexical Choice via Multiple-Sequence Alignment
Regina Barzilay  and  Lillian Lee
Sun 11:15-11:40 (A) NLP Found Helpful (at least for one Text Categorization Task)
Carl Sable, Kathleen McKeown  and  Kenneth Church
Sun 10:25-10:50 (B) A Hybrid Approach to Natural Language Web Search
Jennifer Chu-Carroll, John Prager, Yael Ravin  and  Christian Cesar
Sun 10:50-11:15 (B) A Method for Open-Vocabulary Speech-Driven Text Retrieval
Atsushi Fujii, Katunobu Itou  and  Tetsuya Ishikawa
Sun 11:15-11:40 (B) Manipulating Large Corpora for Text Classification
Fumiyo Fukumoto  and  Yoshimi Suzuki
Sun 11:40-11:50 Short Break
Machine Translation IV (A) / Named Entity Recognition (B)
Sun 11:50-12:15 (A) Processing Comparable Corpora With Bilingual Suffix Trees
Dragos Stefan Munteanu  and  Daniel Marcu
Sun 12:15-12:40 (A) Phrasal Cohesion and Statistical Machine Translation
Heidi Fox
Sun 11:50-12:15 (B) Bootstrapping Named Entity Recognition for Italian Broadcast News
Marcello Federico, Nicola Bertoldi  and  Vanessa Sandrini
Sun 12:15-12:40 (B) Combining Outputs of Multiple Japanese Named Entity Chunkers by Stacking
Takehito Utsuro, Manabu Sassano  and  Kiyotaka Uchimoto
Sun 12:40-2:00 Lunch Break
Lexicons II
Sun 2:00-2:25 Metonymy Resolution as a Classification Task
Katja Markert  and  Malvina Nissim
Sun 2:25-2:50 A Bootstrapping Method for Learning Semantic Lexicons using Extraction Pattern Contexts
Michael Thelen  and  Ellen Riloff
Sun 2:50-3:15 Ensemble Methods for Automatic Thesaurus Extraction
James Curran
Sun 3:15-3:45 Coffee Break
Language Modeling
Sun 3:45-4:10 Using the Web to Overcome Data Sparseness
Frank Keller, Maria Lapata  and  Olga Ourioupina
Sun 4:10-4:35 The SuperARV Language Model: Investigating the Effectiveness of Tightly Integrating Multiple Knowledge Sources
Wen Wang  and  Mary P. Harper
Sun 4:35-5:00 Exploiting Headword Dependency and Predictive Clustering for Language Modeling
Jianfeng Gao, Hisami Suzuki  and  Yang Wen
Sun 5:00-5:10 Short Break
Question Answering / Language Understanding II
Sun 5:10-5:35 An Analysis of the AskMSR Question-Answering System
Eric Brill, Susan Dumais  and  Michele Banko
Sun 5:35-6:00 A Machine-Learning Approach to Introspection in a Question Answering System
Krzysztof Czuba, John Prager  and  Jennifer Chu-Carroll
Sun 6:00-6:25 Extracting Clauses for Spoken Language Understanding in Conversational Systems
Narendra Gupta  and  Srinivas Bangalore
Sun 6:25-6:35 Best Paper Award and Closing Remarks
Reserve Papers
The Influence of Minimum Edit Distance on Reference Resolution
Michael Strube, Stefan Rapp  and  Christoph Müller
Information Extraction from Voicemail Transcripts
Martin Jansche  and  Steven Abney

Web version by David Yarowsky.

EMNLP'02 Home Page
Author Index