First Day: Tuesday, 3 October
8:45	9:00	Introductory Remarks
		Machine Translation Session Chair: Eduard Hovy		Data Oriented Parsing Session Chair: Eric Brill
9:00	9:25	Stephan Vogel and Hermann Ney	Translation with Cascaded Finite State Transducers	Yuval Krymolowski and Ido Dagan	Incorporating Compositional Evidence in Memory-Based Partial Parsing
9:25	9:50	Jung-jae Kim, Key-Sun Choi and Young-Soog Chae	Phrase-Pattern-Based Korean to English Machine Translation using Two Level Translation Pattern Selection	K. Sima'an	Tree-gram Parsing: Lexical Dependencies and Structural Relations
9:50	10:15	George Foster	A Maximum Entropy/Minimum Divergence Translation Model	Rens Bod	An Improved Parser for Data-Oriented Lexical-Functional Analysis
10:15	10:45	Break
		Information Extraction Session Chair: David Yarowsky		Theme Session: Machine Learning in Dialogue Session Chair: Diane Litman
10:45	11:10	Inderjeet Mani and George Wilson	Robust Temporal Processing of News	Robert Malouf	The Order of Prenominal Adjectives in Natural Language Generation
11:10	11:35	Frédéric Béchet, Alexis Nasr and Franck Genet	Tagging Unknown Proper Names Using Decision Trees	Nicholas Roy, Joelle Pineau and Sebastian Thrun	Spoken Dialogue Management using Probabilistic Reasoning
11:40	12:40	Invited Speaker: Susan E. Brennan "Processes that Shape Conversation and their Implications for Computational Linguistics" Introduction by Aravind K. Joshi
12:40	14:30	Lunch
		Partial Parsing Session Chair: Antal van den Bosch		Dialogue and Generation Session Chair: Donia Scott
14:30	14:55	Patrick Pantel and Dekang Lin	An Unsupervised Approach to Prepositional Phrase Attachment using Contextually Similar Words	David Milward	Distributing Representation for Robust Interpretation of Dialogue Utterances
14:55	15:20	Endong Xun, Changning Huang and Ming Zhou	A Unified Statistical Model for the Identification of English BaseNP	Pamela W. Jordan	Can Nominal Expressions Achieve Multiple Goals?: An Empirical Study
15:20	15:45	Grace Ngai and David Yarowsky	Rule Writing or Annotation: Cost-efficient Resource Usage for Base Noun Phrase Chunking	Giuseppe Carenini and Johanna D. Moore	An Empirical Study of the Influence of Argument Conciseness on Argument Effectiveness
15:45	16:10	Alexander Yeh	Using Existing Systems to Supplement Small Amounts of Annotated Grammatical Relations Training Data	Kumiko Tanaka-Ishii and Ian Frank	Multi-Agent Explanation Strategies in Real-Time Domains
16:10	16:40	Break
16:40	18:10	Panel: Computational Linguistics in South and Southeast Asia Panelists: Allan Borra, Bobby Nazief, PHAN Huy Khanh, Rajeev Sangal, Virach Sornlertlamvanich and Zaharin Yusoff Panel Moderator: Aravind K. Joshi

BACK TO TOP

		Second Day: Wednesday, 4 October
		Discourse Session Chair: Julia Hirschberg		Morphology Session Chair: Yuji Matsumoto
8:45	9:10	Antonio Ferrández and Jesús Peral	A Computational Approach to Zero-pronouns in Spanish	Kenneth R. Beesley and Lauri Karttunen	Finite-State Non-Concatenative Morphotactics
9:10	9:35	Thomas S. Morton	Coreference for NLP Applications	Anne De Roeck and Waleed Al-Fares	A Morphologically Sensitive Clustering Algorithm for Identifying Arabic Roots
9:35	10:00	Pamela W. Jordan and Marilyn Walker	Learning Attribute Selections for Non-Pronominal Expressions	David Yarowsky and Richard Wicentowski	Minimally Supervised Morphological Analysis by Multimodal Alignment
10:00	10:30	Break
		Student Research Workshop Session 1		Student Research Workshop Session 2
10:30	11:00	Rosie Jones and Rayid Ghani	Automatically Building a Corpus for a Minority Language from the Web	Tony Mullen	Overfitting Reduction through Feature Merging for Maximum Entropy-Based Parse Selection
11:00	11:30	Kazuhiro Takeuchi	Role of Text Structure for Summary Generation: Clues for Sentence Combination	Daniel Paiva	Investigating style in a corpus of pharmaceutical leaflets: results of a factor analysis
11:40	12:40	Invited Speaker: Jun'ichi Tsujii "Generic NLP Technologies: Language, Knowledge and Information Extraction" Introduction by Hitoshi Iida
12:40	14:30	Lunch
		Phonology Session Chair: Dan Jurafsky		Theme Session: Asian Language Processing Session Chair: Hitoshi Isahara
14:30	14:55	Ewan Klein	A Constraint-based Approach to English Prosodic Constituents	Zheng Chen and Kai-Fu Lee	A New Statistical Approach to Chinese Pinyin Input
14:55	15:20	Karin Müller, Bernd Möbius and Detlef Prescher	Inducing Probabilistic Syllable Classes Using Multivariate Clustering	Lei Zhang, Ming Zhou, Changning Huang and Haihua Pan	Automatic Detecting/Correcting Errors in Chinese Text by an Approximate Word-Matching Algorithm
15:20	15:45	Shimei Pan and Julia Hirschberg	Modeling Local Context for Pitch Accent Prediction	Tom B. Y. Lai and Changning Huang	Dependency-based Syntactic Analysis of Chinese and Annotation of Parsed Corpus
15:45	16:15	Break
		Part of Speech Tagging and Spelling Correction Session Chair: Khalil Sima'an		Theme Session: Summarization Session Chair: Inderjeet Mani
16:15	16:40	Sang-Zoo Lee, Jun'ichi Tsujii and Hae-Chang Rim	Part-of-Speech Tagging Based on Hidden Markov Model Assuming Joint Independence	Adam Berger and Vibhu O. Mittal	Query-Relevant Summarization Using FAQs
16:40	17:05	Silviu Cucerzan and David Yarowsky	Language Independent, Minimally Supervised Induction of Lexical Probabilities	Yoshio Nakao	An Algorithm for One-page Summarization of a Long Text Based on Thematic Hierarchy Detection
17:05	17:30	Mark Hepple	Independence and Commitment: Assumptions for Rapid Training and Execution of Rule-based POS Taggers	Norbert Reithinger, Michael Kipp, Ralf Engel and Jan Alexandersson	Summarizing Multilingual Spoken Negotiation Dialogues
17:30	17:55	Eric Brill and Robert C. Moore	An Improved Error Model for Noisy Channel Spelling Correction	Michele Banko, Vibhu O. Mittal and Michael J. Witbrock	Headline Generation Based on Statistical Translation

BACK TO TOP

		Third Day: Thursday, 5 October
		Information Extraction Session Chair: Sanda Harabagiu		Syntax and Parsing Session Chair: Owen Rambow
9:00	9:25	Kiyotaka Uchimoto, Qing Ma, Masaki Murata, Hiromi Ozaku and Hitoshi Isahara	Named Entity Extraction Based on A Maximum Entropy Model and Transformation Rules	Marcel P. van Lohuizen	Memory-Efficient and Thread-Safe Quasi-Destructive Graph Unification
9:25	9:50	Christopher S.G. Khoo, Syin Chan and Yun Niu	Extracting Causal Knowledge from a Medical Database Using Graphical Patterns	Jonas Kuhn	Processing Optimality-theoretic Syntax by Interleaved Chart Parsing and Generation
9:50	10:15	Chikashi Nobata, Satoshi Sekine and Jun'ichi Tsujii	Difficulty Indices for the Named Entity Task in Japanese	Alexander Koller, Kurt Mehlhorn and Joachim Niehren	A Polynomial-Time Fragment of Dominance Constraints
10:15	10:45	Break
10:45	12:30	Business Meeting
12:30	14:30	Lunch
		Theme Session: Asian Language Processing Session Chair: Ming Zhou		Discourse Session Chair: Robert Dale
14:30	14:55	Sang-Zoo Lee, Jun-ichi Tsujii and Hae-Chang Rim	Hidden Markov Model-Based Korean Part-of-Speech Tagging Considering High Agglutinativity, Word-Spacing, and Lexical Correlativity	M. Poesio, H. Cheng, R. Henschel, J. Hitzeman, R. Kibble and R. Stevenson	Specifying the Parameters of Centering Theory: a Corpus-Based Evaluation using Text from Application-Oriented Domains
14:55	15:20	Masaaki Nagata	Synchronous Morphological Analysis of Grapheme and Phoneme for Japanese OCR	Eleni Miltsakaki and Karen Kukich	The Role of Centering Theory's Rough-Shift in the Teaching and Evaluation of Writing Skills
15:20	15:45	Jin-Xia Huang and Key-Sun Choi	Chinese-Korean Word Alignment Based on Linguistic Comparison	Nancy Ide and Dan Cristea	A Hierarchical Account of Referential Accessibility
15:45	16:15	Break
		Machine Translation Session Chair: Virach Sornlertlamvanich		Parsing and Generation with Lexicalized Grammars Session Chair: John Carroll
16:15	16:40	Eiichiro Sumita	Lexical Transfer Using a Vector-Space Model	William Schuler, David Chiang and Mark Dras	Multi-Component TAG and Notions of Formal Power
16:40	17:05	António Ribeiro, Gabriel Lopes and João Mexia	Using Confidence Bands for Parallel Texts Alignment	David Chiang	Statistical Parsing with an Automatically-Extracted Tree Adjoining Grammar
17:05	17:30	Franz Josef Och and Hermann Ney	Improved Statistical Alignment Models	Srinivas Bangalore and Owen Rambow	Corpus-Based Lexical Choice in Natural Language Generation

BACK TO TOP

		Fourth Day: Friday, 6 October
		Student Research Workshop Session 3		Student Research Workshop Session 4
8:45	9:15	Michael Brasser	Enhancing Traditional Input Methods Through Part-of-Speech Tagging	Holger Schauer	Using Coreferences for Coherence Relations
9:15	9:45	Daniel Bickel	A Statistical Model for Parsing and Word-Sense Disambiguation	Cecile Boisson	Applying Similarity Measures for Management of Textual Templates
9:45	10:15	Burcu Karagol-Ayan	Morphosyntactic Generation of Turkish from Predicate-Argument Structure	Nadjet Bouayad-Agha	Using an abstract rhetorical representation to generate a variety of pragmatically congruent texts
10:15	10:45	Break
		Statistical Parsing Session Chair: Suresh Manandhar		Term Generation Session Chair: Dekang Lin
10:45	11:10	Zhifang Sui, Jun Zhao and Dekai Wu	An Information-Theory-Based Feature Type Analysis for the Modeling of Statistical Parsing	Atsushi Fujii and Tetsuya Ishikawa	Utilizing the World Wide Web as an Encyclopedia: Extracting Term Descriptions from Semi-Structured Texts
11:10	11:35	Stefan Riezler, Detlef Prescher, Jonas Kuhn and Mark Johnson	Lexicalized Stochastic Modeling of Constraint-Based Grammars using Log-Linear Measures and EM Training	Jong-Hoon Oh, KyungSoon Lee and Key-Sun Choi	Term Recognition Using Technical Dictionary Hierarchy
11:40	12:40	Invited Speaker: Roger K. Moore "Spoken Language Technology: Where Do We Go From Here?" Introduction by Wolfgang Wahlster
12:40	14:30	Lunch
		Semantics Session Chair: Martha Palmer		Theme Session: Asian Language Processing Session Chair: Rajeev Sangal
14:30	14:55	J. Daudé, L. Padró, and G. Rigau	Mapping WordNets Using Structural Information	Ting Liu, Ming Zhou, Jianfeng Gao, Endong Xun and Changning Huang	PENS: A Machine-aided English Writing System for Chinese Users
14:55	15:20	Daniel Gildea and Daniel Jurafsky	Automatic Labeling of Semantic Roles	Jun-ichi Kakegawa, Hisayuki Kanda, Eitaro Fujioka, Makoto Itami and Kohji Itoh	Diagnostic Processing of Japanese for Computer-Assisted Second Language Learning
15:20	15:45	Manfred Pinkal and Michael Kohlhase	Feature Logic for Dotted Types: A Formalism for Complex Word Meanings	Seong-Bae Park, Byoung-Tak Zhang and Yung Taek Kim	Word Sense Disambiguation by Learning from Unlabeled Data
15:45	16:15	Break
		Theme Session: Question-Answering Session Chair: Sanda Harabagiu		Smoothing Session Chair: Ken Church
16:15	16:40	José Luis Vicedo and Antonio Ferrández	Importance of Pronominal Anaphora Resolution in Question Answering Systems	Kilyoun Kim and Key-Sun Choi	Dimension-Reduced Estimation of Word Co-occurrence Probability
16:40	17:05	Dan Moldovan, Sanda Harabagiu, Marius Pasca, Rada Mihalcea, Roxana Girju, Richard Goodrum and Vasile Rus	The Structure and Performance of an Open-Domain Question Answering System	Jianfeng Gao and Kai-Fu Lee	Distribution-Based Pruning of Backoff Language Models

BACK TO TOP

Susan E. Brennan

• Associate Professor and Cognitive/Experimental Area Head, Department of Psychology, State University of New York at Stony Brook, USA
• Associate Editor, Discourse Processes

Roger K. Moore

• Chief Scientific Officer, 20/20 Speech Ltd.,
• Visiting Professor, University College London
• President, International Speech Communication Association
• President, Permanent Council of the International Conference on Spoken Language Processing

Jun'ichi Tsujii

• Professor, Department of Information Science, University of Tokyo, Japan
• Professor of Computational Linguistics, Centre for Computational Linguistics , University of Science and Technology in Manchester (UMIST), UK

BACK TO TOP

In this paper, we will discuss how we can combine more sophisticated, linguistically elaborate techniques with the current statistical techniques and what kinds of improvement we can expect from such an integration of different knowledge types and methods.

This talk will illuminate these issues, and will conclude with an analysis of the options for future spoken language R&D.

BACK TO TOP

Professor Wolfgang Wahlster will deliver the Presidential Address.

BACK TO TOP