ACL 2003 Main Session Conference Program

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