Proceedings of the 2003 Conference on Empirical Methods in NLP

Friday, July 11, 2003
8:20-8:30 Welcome
Session 1: Multilingual Methods, and Paraphrasing
8:30-8:55 A Projection Extension Algorithm for Statistical Machine Translation
Christoph Tillmann
8:55-9:20 Statistical Machine Translation Using Coercive Two-Level Syntactic Transduction
Charles Schafer  and  David Yarowsky
9:20-9:45 Cross-Lingual Lexical Triggers in Statistical Language Modeling
Woosung Kim  and  Sanjeev Khudanpur
9:45-10:10 Sentence Alignment for Monolingual Comparable Corpora
Regina Barzilay  and  Noemie Elhadad
10:10-10:35 Break
Session 2: Predicate-Argument Structure
10:35-11:00 Antecedent Recovery: Experiments with a Trace Tagger
Péter Dienes  and  Amit Dubey
11:00-11:25 Use of Deep Linguistic Features for the Recognition and Labeling of Semantic Arguments
John Chen  and  Owen Rambow
11:25-11:50 Maximum Entropy Models for FrameNet Classification
Michael Fleischman, Namhee Kwon  and  Eduard Hovy
11:50-12:15 Identifying Semantic Roles Using Combinatory Categorial Grammar
Daniel Gildea  and  Julia Hockenmaier
12:15-2:00 Lunch
Invited Talk
2:00-3:00 Knight, Kevin: Deeper Representations for Machine Translation: Ready or Not?
3:00-3:30 Break
Session 3: New Methods
3:30-3:55 Variation of Entropy and Parse Trees of Sentences as a Function of the Sentence Number
Dmitriy Genzel  and  Eugene Charniak
3:55-4:20 A Plethora of Methods for Learning English Countability
Timothy Baldwin  and  Francis Bond
4:20-4:45 A General Framework for Distributional Similarity
Julie Weeds  and  David Weir
4:45-5:10 Break
Session 4: Parsing
5:10-5:35 Using LTAG Based Features in Parse Reranking
Libin Shen, Anoop Sarkar  and  Aravind Joshi
5:35-6:00 Log-Linear Models for Wide-Coverage CCG Parsing
Stephen Clark  and  James Curran
Saturday, July 12, 2003
Session 5: Semantics and Generation
8:30-8:55 Learning Extraction Patterns for Subjective Expressions
Ellen Riloff  and  Janyce Wiebe
8:55-9:20 Bootstrapping Coreference Classifiers with Multiple Machine Learning Algorithms
Vincent Ng  and  Claire Cardie
9:20-9:45 Statistical Acquisition of Content Selection Rules for Natural Language Generation
Pablo Ariel Duboue  and  Kathleen R McKeown
9:45-10:10 Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences
Hong Yu  and  Vasileios Hatzivassiloglou
10:10-10:35 Break
Session 6: Maximum-Entropy Methods, and Alternatives
10:35-11:00 Evaluation and Extension of Maximum Entropy Models with Inequality Constraints
Jun'ichi Kazama  and  Jun'ichi Tsujii
11:00-11:25 Investigating Loss Functions and Optimization Methods for Discriminative Learning of Label Sequences
Yasemin Altun, Mark Johnson  and  Thomas Hofmann
11:25-11:50 A Fast Algorithm for Feature Selection in Conditional Maximum Entropy Modeling
Yaqian Zhou, Fuliang Weng, Lide Wu  and  Hauke Schmidt
11:50-12:15 Training Connectionist Models for the Structured Language Model
Peng Xu, Ahmad Emami  and  Frederick Jelinek
12:15-2:00 Lunch
Session 7: Word Sense Disambiguation and Anaphora
2:00-2:25 Supersense Tagging of Unknown Nouns in WordNet
Massimiliano Ciaramita  and  Mark Johnson
2:25-2:50 Using the Web in Machine Learning for Other-Anaphora Resolution
Natalia N. Modjeska, Katja Markert  and  Malvina Nissim
2:50-3:15 Japanese Zero Pronoun Resolution based on Ranking Rules and Machine Learning
Hideki Isozaki  and  Tsutomu Hirao
3:15-3:40 Break
Session 8: Asian Languages/Information Retrieval
3:40-4:05 A Maximum Entropy Chinese Character-Based Parser
Xiaoqiang Luo
4:05-4:30 HowtogetaChineseName(Entity): Segmentation and Combination Issues
Hongyan Jing, Radu Florian, Xiaoqiang Luo, Tong Zhang  and  Abraham Ittycheriah
4:30-4:55 Virtual Examples for Text Classification with Support Vector Machines
Manabu Sassano
4:55-5:20 Improved Automatic Keyword Extraction Given More Linguistic Knowledge
Anette Hulth
5:20-5:30 Best Paper Award