| TUESDAY, JUNE 5 | ||||
|---|---|---|---|---|
| 8:30 | 5:00 | CONFERENCE REGISTRATION | ||
| 8:45 | 9:00 | OPENING REMARKS | ||
| SESSION 1: Natural Language Generation | ||||
| 9:00 | 9:25 | Instance-Based Natural Language Generation | ||
| Sebastian Varges and Chris Mellish | ||||
| 9:25 | 9:50 | Corpus-based NP Modifier Generation | ||
| Hua Cheng, Massimo Poesio, Renate Henschel and Chris Mellish | ||||
| 9:50 | 10:15 | SPoT: A Trainable Sentence Planner | ||
| Marilyn A. Walker, Owen Rambow and Monica Rogati | ||||
| 10:15 | 10:45 | BREAK | ||
| SESSION 2: Information Retrieval and Machine Learning | ||||
| 10:45 | 11:10 | Why Inverse Document Frequency? | ||
| Kishore Papineni | ||||
| 11:10 | 11:35 | Question Answering Using Maximum-Entropy Components | ||
| Abraham Ittycheriah, Martin Franz, Wei-Jing Zhu and Adwait Ratnaparkhi | ||||
| 11:35 | 12:00 | Transformation Based Learning in the Fast Lane | ||
| Grace Ngai and Radu Florian | ||||
| 12:00 | 2:00 | LUNCH | ||
| 2:00 | 3:00 | INVITED TALK: Tom Mitchell, Carnegie Mellon University and WhizBang! Labs "Machine Learning and Extracting Information from the Web" | ||
| SESSION 3: Names and Coreference | ||||
| 3:05 | 3:30 | Unsupervised Learning of Name Structure From Coreference Data | ||
| Eugene Charniak | ||||
| 3:30 | 3:55 | Text and Knowledge Mining for Coreference Resolution | ||
| Sanda M. Harabagiu, Razvan C. Bunescu and Steven J. Maiorano | ||||
| 3:55 | 4:30 | BREAK | ||
| SESSION 4: Word Meaning | ||||
| 4:30 | 4:55 | A Corpus-based Account of Regular Polysemy: The Case of Context-sensitive Adjectives | ||
| Maria Lapata | ||||
| 4:55 | 5:20 | Tree-Cut and a Lexicon Based on Systematic Polysemy | ||
| Noriko Tomuro | ||||
| 5:20 | 5:45 | A Decision Tree of Bigrams is an Accurate Predictor of Word Sense | ||
| Ted Pedersen | ||||
| WEDNESDAY, JUNE 6 | ||||
|---|---|---|---|---|
| 8:30 | 5:00 | CONFERENCE REGISTRATION | ||
| SESSION 5: Semantics | ||||
| 9:00 | 9:25 | An Algorithm for Aspects of Semantic Interpretation Using an Enhanced WordNet | ||
| Fernando Gomez | ||||
| 9:25 | 9:50 | Class-Based Probability Estimation Using a Semantic Hierarchy | ||
| Stephen Clark and David Weir | ||||
| 9:50 | 10:15 | Identifying Cognates by Phonetic and Semantic Similarity | ||
| Grzegorz Kondrak | ||||
| 10:15 | 10:45 | BREAK | ||
| SESSION 6: Speech Synthesis and Recognition | ||||
| 10:45 | 11:10 | Re-Engineering Letter-to-Sound Rules | ||
| Martin Jansche | ||||
| 11:10 | 11:35 | Edit Detection and Parsing for Transcribed Speech | ||
| Eugene Charniak and Mark Johnson | ||||
| 11:35 | 12:00 | Generating Training Data for Medical Dictations | ||
| Sergey Pakhomov, Michael Schonwetter and Joan Bachenko | ||||
| 12:00 | 2:00 | LUNCH | ||
| 2:00 | 3:00 | NAACL BUSINESS MEETING | ||
| 3:00 | 4:00 | INVITED TALK: Jon Kleinberg, Cornell University "Structure and Content in World Wide Web Search" | ||
| 4:00 | 4:30 | BREAK | ||
| SESSION 7: Machine Translation | ||||
| 4:30 | 4:55 | A Finite-State Approach to Machine Translation | ||
| Srinivas Bangalore and Giuseppe Riccardi | ||||
| 4:55 | 5:20 | Information-Based Machine Translation | ||
| Keiko Horiguchi | ||||
| 5:20 | 5:45 | Multipath Translation Lexicon Induction via Bridge Languages | ||
| Gideon S. Mann and David Yarowsky | ||||
| THURSDAY, JUNE 7 | ||||
|---|---|---|---|---|
| 8:30 | 12:00 | CONFERENCE REGISTRATION | ||
| SESSION 8: Parsing | ||||
| 9:00 | 9:25 | A Probabilistic Earley Parser as a Psycholinguistic Model | ||
| John Hale | ||||
| 9:25 | 9:50 | Refining Tabular Parsers for TAGs | ||
| Éric Villemonte de la Clergerie | ||||
| 9:50 | 10:15 | Applying Co-Training Methods to Statistical Parsing | ||
| Anoop Sarkar | ||||
| 10:15 | 10:45 | BREAK | ||
| SESSION 9: Morphology and Chunking | ||||
| 10:45 | 11:10 | Knowledge-Free Induction of Inflectional Morphologies | ||
| Patrick Schone and Daniel Jurafsky | ||||
| 11:10 | 11:35 | Chunking with Support Vector Machines | ||
| Taku Kudo and Yuji Matsumoto | ||||
| 11:35 | 12:00 | Inducing Multilingual POS Taggers and NP Bracketers via Robust Projection Across Aligned Corpora | ||
| David Yarowsky and Grace Ngai | ||||
| 12:00 | 2:00 | LUNCH | ||
| 2:00 | 3:00 | INVITED TALK: Aravind Joshi, University of Pennsylvania "Language Modeling of Biological Data" | ||
| SESSION 10: Natural Language Dialogue | ||||
| 3:05 | 3:30 | Identifying User Corrections Automatically in Spoken Dialogue Systems | ||
| Julia Hirschberg, Diane Litman and Marc Swerts | ||||
| 3:30 | 3:55 | Learning Optimal Dialogue Management Rules by Using Reinforcement Learning and Inductive Logic Programming | ||
| Renaud Lecoeuche | ||||
| 3:55 | 4:30 | BREAK | ||
| SESSION 11: Language Modeling | ||||
| 4:30 | 4:55 | A Structured Language Model Based on Context-Sensitive Probabilistic Left-Corner Parsing | ||
| Dong Hoon Van Uytsel, Filip Van Aelten and Dirk Van Compernolle | ||||
| 4:55 | 5:20 | Do CFG-Based Language Models Need Agreement Constraints? | ||
| Manny Rayner, Genevieve Gorrell, Beth Ann Hockey, John Dowding and Johan Boye | ||||
| 5:20 | 5:45 | You're Not From 'Round Here, Are You? Naive Bayes Detection of Non-Native Utterances | ||
| Laura Mayfield Tomokiyo and Rosie Jones | ||||