| First Day: Tuesday, July 8, 2003 |
|
| 9:00-9:30 |
Opening Session |
| 9:30-10:30 |
Invited Talk: Layout in NLP: The Case for Document Structure |
|
Donia Scott |
| 10:30-11:00 |
Break |
|
Session 1: Question Answering |
|
| 11:00-11:25 |
Offline Strategies for Online Question Answering: Answering Questions Before They Are Asked |
|
Michael Fleischman, Eduard Hovy and Abdessamad Echihabi |
| 11:25-11:50 |
Using Predicate-Argument Structures for Information Extraction |
|
Mihai Surdeanu, Sanda Harabagiu, John Williams and Paul Aarseth |
| 11:50-12:15 |
A Noisy-Channel Approach to Question Answering |
|
Abdessamad Echihabi and Daniel Marcu |
|
Session 2: Machine Larning: Kernels |
|
| 11:00-11:25 |
Fast Methods for Kernel-Based Text Analysis |
|
Taku Kudo and Yuji Matsumoto |
| 11:25-11:50 |
Hierarchical Directed Acyclic Graph Kernel: Methods for Structured Natural Language Data |
|
Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki and Eisaku Maeda |
| 11:50-12:15 |
Generalized Algorithms for Constructing Statistical Language Models |
|
Cyril Allauzen, Mehryar Mohri and Brian Roark |
|
Session 3: Subcategorization and Word Meaning |
|
| 11:00-11:25 |
Improving Subcategorization Acquisition Using Word Sense Disambiguation |
|
Anna Korhonen and Judita Preiss |
| 11:25-11:50 |
Syntactic Features and Word Similarity for Supervised Metonymy Resolution |
|
Malvina Nissim and Katja Markert |
| 11:50-12:15 |
Clustering Polysemic Subcategorization Frame Distributions Semantically |
|
Anna Korhonen, Yuval Krymolowski and Zvika Marx |
| 12:15-14:00 |
Lunch |
|
Session 1: Alignment for Machine Translation |
|
| 14:00-14:25 |
Reliable Measures for Aligning Japanese-English News Articles and Sentences |
|
Masao Utiyama and Hitoshi Isahara |
| 14:25-14:50 |
Loosely Tree-Based Alignment for Machine Translation |
|
Daniel Gildea |
| 14:50-15:15 |
A Probability Model to Improve Word Alignment |
|
Colin Cherry and Dekang Lin |
|
Session 2: Parsing German |
|
| 14:00-14:25 |
Probabilistic Parsing for German Using Sister-Head Dependencies |
|
Amit Dubey and Frank Keller |
| 14:25-14:50 |
Integrated Shallow and Deep Parsing: TopP Meets HPSG |
|
Anette Frank, Markus Becker, Berthold Crysmann, Bernd Kiefer and Ulrich Schäfer |
| 14:50-15:15 |
Combining Deep and Shallow Approaches in Parsing German |
|
Michael Schiehlen |
|
Session 3: Vector Space Models |
|
| 14:00-14:25 |
Synonymous Collocation Extraction Using Translation Information |
|
Hua Wu and Ming Zhou |
| 14:25-14:50 |
Constructing Semantic Space Models from Parsed Corpora |
|
Sebastian Padó and Mirella Lapata |
| 14:50-15:15 |
Orthogonal Negation in Vector Spaces for Modelling Word-Meanings and Document Retrieval |
|
Dominic Widdows |
| 15:15-15:45 |
Break |
|
Session 1: Statistical Machine Translation |
|
| 15:45-16:10 |
A Comparative Study on Reordering Constraints in Statistical Machine Translation |
|
Richard Zens and Hermann Ney |
| 16:10-16:35 |
tRuEcasIng |
|
Lucian Vlad Lita, Abe Ittycheriah, Salim Roukos and Nanda Kambhatla |
| 16:35-17:00 |
Minimum Error Rate Training in Statistical Machine Translation |
|
Franz Josef Och |
|
Session 2: Coreference in Discourse and Dialogue |
|
| 15:45-16:10 |
A Machine Learning Approach to Pronoun Resolution in Spoken Dialogue |
|
Michael Strube and Christoph Müller |
| 16:10-16:35 |
Coreference Resolution Using Competition Learning Approach |
|
Xiaofeng Yang, Guodong Zhou, Jian Su and Chew Lim Tan |
|
Session 3: Rule-based Parsing |
|
| 15:45-16:10 |
Generating Parallel Multilingual LFG-TAG Grammars from a MetaGrammar |
|
Lionel Clément and Alexandra Kinyon |
| 16:10-16:35 |
Compounding and Derivational Morphology in a Finite-State Setting |
|
Jonas Kuhn |
| 16:35-17:00 |
A Tabulation-Based Parsing Method that Reduces Copying |
|
Gerald Penn and Cosmin Munteanu |
| 17:00-17:15 |
Break |
| 17:15-18:15 |
Invited Talk: Economics about Language |
|
Ariel Rubinstein |
| Second Day: Wednesday, July 9, 2003 |
|
Session 1: Information Retrieval |
|
| 9:00-9:25 |
Recognizing Expressions of Commonsense Psychology in English Text |
|
Andrew Gordon, Abe Kazemzadeh, Anish Nair and Milena Petrova |
| 9:25-9:50 |
Closing the Gap: Learning-Based Information Extraction Rivaling Knowledge-Engineering Methods |
|
Hai Leong Chieu, Hwee Tou Ng and Yoong Keok Lee |
| 9:50-10:15 |
An Improved Extraction Pattern Representation Model for Automatic IE Pattern Acquisition |
|
Kiyoshi Sudo, Satoshi Sekine and Ralph Grishman |
| 10:15-10:40 |
Optimizing Story Link Detection is not Equivalent to Optimizing New Event Detection |
|
Ayman Farahat, Francine Chen and Thorsten Brants |
|
Session 2: Spoken Dialog |
|
| 9:00-9:25 |
Corpus-Based Discourse Understanding in Spoken Dialogue Systems |
|
Ryuichiro Higashinaka, Mikio Nakano and Kiyoaki Aikawa |
| 9:25-9:50 |
Extracting Key Semantic Terms from Chinese Speech Query for Web Searches |
|
Gang Wang, Tat-Seng Chua and Yong-Cheng Wang |
| 9:50-10:15 |
Flexible Guidance Generation Using User Model in Spoken Dialogue Systems |
|
Kazunori Komatani, Shinichi Ueno, Tatsuya Kawahara and Hiroshi G. Okuno |
| 10:15-10:40 |
Integrating Discourse Markers into a Pipelined Natural Language Generation Architecture |
|
Charles B. Callaway |
|
Session 3: Statistical Modeling |
|
| 9:00-9:25 |
Improved Source-Channel Models for Chinese Word Segmentation |
|
Jianfeng Gao, Mu Li and Chang-Ning Huang |
| 9:25-9:50 |
Unsupervised Segmentation of Words Using Prior Distributions of Morph Length and Frequency |
|
Mathias Creutz |
| 9:50-10:15 |
Parametric Models of Linguistic Count Data |
|
Martin Jansche |
| 10:15-10:40 |
Self-Organizing Markov Models and Their Application to Part-of-Speech Tagging |
|
Jin-Dong Kim, Hae-Chang Rim and Jun'ich Tsujii |
| 10:40-11:20 |
Break |
| 11:20-12:20 |
ACL Business Meeting |
| 12:20-14:00 |
Lunch |
| 14:00-15:10 |
Lifetime Achievement Award Session |
| 15:10-15:40 |
Break |
|
Session 1: Machine Translation and Chunking |
|
| 15:40-16:05 |
Chunk-Based Statistical Translation |
|
Taro Watanabe, Eiichiro Sumita and Hiroshi G. Okuno |
| 16:05-16:30 |
Feature-Rich Statistical Translation of Noun Phrases |
|
Philipp Koehn and Kevin Knight |
| 16:30-16:55 |
Effective Phrase Translation Extraction from Alignment Models |
|
Ashish Venugopal, Stephan Vogel and Alex Waibel |
|
Session 2: Named Entities and Bootstraping |
|
| 15:40-16:05 |
Uncertainty Reduction in Collaborative Bootstrapping: Measure and Algorithm |
|
Yunbo Cao, Hang Li and Li Lian |
| 16:05-16:30 |
A Bootstrapping Approach to Named Entity Classification Using Successive Learners |
|
Cheng Niu, Wei Li, Jihong Ding and Rohini Srihari |
| 16:30-16:55 |
Counter-Training in Discovery of Semantic Patterns |
|
Roman Yangarber |
|
Session 3: Parsing and Grammar Formalisms |
|
| 15:40-16:05 |
k-Valued Non-Associative Lambek Categorial Grammars are not Learnable from Strings |
|
Denis Béchet and Annie Foret |
| 16:05-16:30 |
Parsing with Generative Models of Predicate-Argument Structure |
|
Julia Hockenmaier |
| 16:30-16:55 |
Bridging the Gap Between Underspecification Formalisms: Minimal Recursion Semantics as Dominance Constraints |
|
Joachim Niehren and Stefan Thater |
| 16:55-17:20 |
Break |
|
Session 1: Summarization |
|
| 17:20-17:45 |
Evaluation Challenges in Large-Scale Document Summarization |
|
Dragomir R. Radev, Simone Teufel, Horacio Saggion, Wai Lam, John Blitzer, Hong Qi, Arda Çelebi, Danyu Liu and Elliott Drabek |
| 17:45-18:10 |
Analysis of Source Identified Text Corpora: Exploring the Statistics of the Reused Text and Authorship |
|
Akiko Aizawa |
|
Session 2: Word Segmentation for Arabic |
|
| 17:20-17:45 |
Unsupervised Learning of Arabic Stemming Using a Parallel Corpus |
|
Monica Rogati, Scott McCarley and Yiming Yang |
| 17:45-18:10 |
Language Model Based Arabic Word Segmentation |
|
Young-Suk Lee, Kishore Papineni, Salim Roukos, Ossama Emam and Hany Hassan |
|
Session 3: Language Acquisition |
|
| 17:20-17:45 |
Acquiring Vocabulary for Predictive Text Entry through Dynamic Reuse of a Small User Corpus |
|
Kumiko Tanaka-Ishii, Daichi Hayakawa and Masato Takeichi |
| 17:45-18:10 |
A Word-Order Database for Testing Computational Models of Language Acquisition |
|
William Gregory Sakas |
| Third Day: Thursday, July 10, 2003 |
|
Session 1: Probabilistic Parsing |
|
| 9:00-9:25 |
Accurate Unlexicalized Parsing |
|
Dan Klein and Christopher D. Manning |
| 9:25-9:50 |
Deep Syntactic Processing by Combining Shallow Methods |
|
Péter Dienes and Amit Dubey |
| 9:50-10:15 |
Is it Harder to Parse Chinese, or the Chinese Treebank? |
|
Roger Levy and Christopher Manning |
|
Session 2: Word Sense Disambiguation and Machine Translation |
|
| 9:00-9:25 |
Feedback Cleaning of Machine Translation Rules Using Automatic Evaluation |
|
Kenji Imamura, Eiichiro Sumita and Yuji Matsumoto |
| 9:25-9:50 |
Exploiting Parallel Texts for Word Sense Disambiguation: An Empirical Study |
|
Hwee Tou Ng, Bin Wang and Yee Seng Chan |
| 9:50-10:15 |
Learning the Countability of English Nouns from Corpus Data |
|
Timothy Baldwin and Francis Bond |
|
Session 3: Phonology and Morphology |
|
| 9:00-9:25 |
A Syllable Based Word Recognition Model for Korean Noun Extraction |
|
Do-Gil Lee, Hae-Chang Rim and Heui-Seok Lim |
| 9:25-9:50 |
Morphological Analysis of a Large Spontaneous Speech Corpus in Japanese |
|
Kiyotaka Uchimoto, Chikashi Nobata, Atsushi Yamada, Satoshi Sekine and Hitoshi Isahara |
| 9:50-10:15 |
Learning to Predict Pitch Accents and Prosodic Boundaries in Dutch |
|
Erwin Marsi, Martin Reynaert, Antal van den Bosch, Walter Daelemans and Véronique Hoste |
| 10:15-10:30 |
Break |
| 10:30-12:15 |
Student Research Workshop |
| 12:15-14:00 |
Lunch |
|
Session 1: Chunk Parsing |
|
| 14:00-14:25 |
Text Chunking by Combining Hand-Crafted Rules and Memory-Based Learning |
|
Seong-Bae Park and Byoung-Tak Zhang |
| 14:25-14:50 |
A SNoW Based Supertagger with Application to NP Chunking |
|
Libin Shen and Aravind K. Joshi |
| 14:50-15:15 |
An Expert Lexicon Approach to Identifying English Phrasal Verbs |
|
Wei Li, Xiuhong Zhang, Cheng Niu, Yuankai Jiang and Rohini K. Srihari |
|
Session 2: Parsing and Semantics |
|
| 14:00-14:25 |
Unsupervised Learning of Dependency Structure for Language Modeling |
|
Jianfeng Gao and Hisami Suzuki |
| 14:25-14:50 |
Using Model-Theoretic Semantic Interpretation to Guide Statistical Parsing and Word Recognition in a Spoken Language Interface |
|
William Schuler |
| 14:50-15:15 |
Towards a Resource for Lexical Semantics: A Large German Corpus with Extensive Semantic Annotation |
|
Katrin Erk, Andrea Kowalski, Sebastian Padó and Manfred Pinkal |
|
Session 3: Discourse and Dialogue Segmentation |
|
| 14:00-14:25 |
Probabilistic Text Structuring: Experiments with Sentence Ordering |
|
Mirella Lapata |
| 14:25-14:50 |
Towards a Model of Face-to-Face Grounding |
|
Yukiko Nakano, Gabe Reinstein, Tom Stocky and Justine Cassell |
| 14:50-15:15 |
Discourse Segmentation of Multi-Party Conversation |
|
Michel Galley, Kathleen R. McKeown, Eric Fosler-Lussier and Hongyan Jing |
| 15:15-15:45 |
Break |
| 15:45-16:45 |
Invited Talk: From Structure to Meaning: Simple Sentence-Structure Cues Guide Sentence Comprehension by Young Children |
|
Cynthia Fisher |
| 16:45-17:10 |
Best Paper Award Ceremony and Closing Session |