|
|
|
|
|
|
|
|
|
|
|
Technical Program |
|
May 2-7, 2004
The Park Plaza Hotel,
one block from the Boston Common
|
|
|
Accepted Full Papers
- Ensemble-based Active Learning for Parse Selection
- Jason Baldridge and
Miles Osborne (University of Edinburgh)
- Balancing data-driven and rule-based approaches in the context of a Multimodal Conversational System
- Srinivas Bangalore and
Michael Johnston (AT&T Labs-Research)
- Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization
- Regina Barzilay (MIT) and
Lillian Lee (Cornell University)
- Unsupervised Learning of Contextual Role Knowledge for Coreference Resolution
- David Bean and
Ellen Riloff (University of Utah)
- Multiple Similarity Measures and Source-Pair Information in Story Link Detection
- Francine Chen,
Ayman Farahat, and
Thorsten Brants (Palo Alto Research Center)
- A Salience-Based Approach to Gesture-Speech Alignment
- Jacob Eisenstein and
C. Mario Christoudias (MIT Computer Science and Artificial Intelligence Laboratory)
- A Statistical Model for Multilingual Entity Detection and Tracking
- Radu Florian,
H. Hassan (*),
A. Ittycheriah,
Hongyan Jing,
Nanda Kambhatla,
X. Luo,
Nicolas Nicolov,
Salim Roukos, and
T. Zhang (IBM T.J. Watson Research Center, *IBM Egypt)
- What's in a translation rule?
- Michel Galley (Columbia University),
Mark Hopkins (UCLA),
Kevin Knight (USC/ISI), and
Daniel Marcu (USC/ISI)
- Training Tree Transducers
- Jonathan Graehl and
Kevin Knight (USC/ISI)
- Exponential Priors for Maximum Entropy Models
- Joshua Goodman (Microsoft Research)
- Sentence-Internal Prosody Does not Help Parsing the Way Punctuation Does
- Michelle Gregory (Buffalo),
Mark Johnson (Brown), and
Eugene Charniak (Brown)
- Cross-Document Coreference on a Large Scale Corpus
- Chung Heong Gooi and
James Allan (UMass)
- Evaluating Multiple Aspects of Coherence in Student Essays
- Derrick Higgins (ETS),
Jill Burstein (ETS),
Daniel Marcu (USC/ISI), and
Claudia Gentile (ETS)
- Answering Definition Questions with Multiple Knowledge Sources
- Wesley Hildebrandt,
Boris Katz,
and Jimmy Lin (MIT CSAIL)
- Optimizing Automated Call Routing by Integrating Spoken Dialog Models with Queuing Models
- Tim Paek and
Eric Horvitz (Microsoft Research)
- Improving Named Entity Translation Combining Phonetic and Semantic Similarities
- Fei Huang,
Stephan Vogel, and
Alex Waibel (CMU/LTI)
- Paraphrasing Predicates from Written Language to Spoken Language Using the Web
- Nobuhiro Kaji (Tokyo University),
Masashi Okamoto (Osaka University), and
Sadao Kurohashi (Tokyo University)
- Speed and Accuracy in Shallow and Deep Stochastic Parsing
- Ron Kaplan,
Stefan Riezler,
Tracy H. King,
John T. Maxwell III,
Alex Vasserman, and
Richard Crouch (Palo Alto Research Center)
- The (Non)Utility of Predicate-Argument Frequencies for Pronoun Interpretation
- Andrew Kehler (UCSD Linguistics),
Douglas Appelt (SRI International),
Lara Taylor (UCSD Linguistics), and
Aleksandr Simma (UCSD Computer Science)
- Detecting Structural Metadata with Decision Trees and Transformation-Based Learning
- Joungbum Kim,
Sarah E. Schwarm, and
Mari Ostendorf (University of Washington)
- Minimum Bayes-Risk Decoding for Statistical Machine Translation
- Shankar Kumar and William Byrne (JHU)
- A Probabilistic Rasch Analysis of Question Answering Evaluations
- Rense Lange (Integrated Knowledge Systems & the Illinois State Board of Education),
Juan Moran (University of Illinois at Urbana-Champaign),
Warren R. Greiff (MITRE), and
Lisa Ferro (MITRE)
- The Web as a Baseline: Evaluating the Performance of Unsupervised Web-based Models for a Range of NLP Tasks
- Mirella Lapata (University of Sheffield) and
Frank Keller (University of Edinburgh)
- Inferring Sentence-internal Temporal Relations
- Mirella Lapata (University of Sheffield) and
Alex Lascarides (University of Edinburgh)
- Robust Reading of Ambiguous Writing
- Xin Li,
Paul Morie, and
Dan Roth (University of Illinois at Urbana-Champaign)
- Predicting Emotion in Spoken Dialogue from Multiple Knowledge Sources
- Diane Litman and
Kate Forbes-Riley (University of Pittsburgh)
- A Language Modeling Approach to Predicting Reading Difficulty
- Kevyn Collins-Thompson,
James P. Callan
(CMU/LTI)
- Name Tagging with Word Clusters and Discriminative Training
- Scott Miller, Jethran Guinness, Alex Zamanian (BBN)
- Improved Machine Translation Performance via Parallel Sentence Extraction from Comparable Corpora
- Dragos Munteanu,
Alexander Fraser, and
Daniel Marcu (USC/ISI)
- Evaluating Content Selection in Summarization: The Pyramid Method
- Ani Nenkova and
Rebecca Passonneau (Columbia University)
- A Smorgasbord of Features for Statistical Machine Translation
- Franz Josef Och (USC/ISI),
Daniel Gildea (Rochester University),
Sanjeev Khudanpur (JHU),
Anoop Sarkar (Simon Fraser University),
Kenji Yamada (PARC),
Alex Fraser (USC/ISI),
Shankar Kumar (JHU),
Libin Shen (UPenn),
David Smith (JHU),
Katherine Eng (Stanford University),
Viren Jain (UPenn),
Zhen Jin (Mt Holyoke), and
Dragomir Radev (UMich)
- Automatically Labeling Semantic Classes
- Patrick Pantel (USC/ISI) and
Deepak Ravichandran (USC/ISI)
- Accurate Information Extraction from Research Papers using Conditional Random Fields
- Fuchun Peng and
Andrew McCallum (UMass)
- Shallow Semantic Parsing using Support Vector Machines
- Sameer S. Pradhan (University of Colorado at Boulder),
Wayne H. Ward (University of Colorado at Boulder),
Kadri Hacioglu (University of Colorado at Boulder),
James H. Martin (University of Colorado at Boulder), and
Dan Jurafsky (Stanford University)
- The Tao of CHI: Towards Effective Human-Computer Interaction
- Robert Porzel and
Manja Baudis (European Media Laboratory, GmbH)
- Non-Native Users in the Let's Go!! Spoken Dialogue System: Dealing with Linguistic Mismatch
- Antoine Raux and
Maxine Eskenazi (CMU/LTI)
- Lattice-Based Search for Spoken Utterance Retrieval
- Murat Saraclar (AT&T Research Labs) and
Richard Sproat (University of Illinois at Urbana-Champaign)
- Discriminative Reranking for Machine Translation
- Libin Shen (UPenn),
Anoop Sarkar (Simon Fraser University), and
Franz Josef Och (USC/ISI)
- Acquiring Hyponymy Relations from Web Documents
- Keiji Shinzato and
Kentaro Torisawa (Japan Advanced Institute of Science and Technology)
- Automatic Question Answering: Beyond the Factoid
- Radu Soricut (USC/ISI) and
Eric Brill (Microsoft Research)
- Shallow Semantc Parsing of Chinese
- Honglin Sun and Daniel Jurafsky (University of Colorado at Boulder)
- Comparison of two interactive search refinement techniques
- Olga Vechtomova (University of Waterloo) and
Murat Karamuftuoglu (Bilkent University)
- Improvements in Phrase-Based Statistical Machine Translation
- Richard Zens and
Hermann Ney (RWTH Aachen)
Accepted Short Papers
- Using N-Grams To Understand the Nature of Summaries
- Michele Banko and
Lucy Vanderwende (Microsoft Research)
- Multi-Speaker Language Modeling
- Jeff Bilmes (University of Washington, Seattle)
- Performance Evaluation and Error Analysis for Multimodal Reference Resolution in a Conversation System
- Joyce Y. Chai (Michigan State University),
Zahar Prasov (Michigan State University), and
(Pengyu Hong - Harvard University)
- Automatic Construction of an English-Chinese Bilingual FrameNet
- Benfeng Chen and Pascale Fung (HKUST)
- Web Search Intent Induction via Automatic Query Reformulation
- Hal Daume III (USC/ISI) and
Eric Brill (Microsoft Research)
- A Lightweight Semantic Chunker Based on Tagging
- Kadri Hacioglu (University of Colorado at Boulder)
- Advances in Children's Speech Recognition within an Interactive Literacy Tutor
- Andreas Hagen,
Bryan Pellom,
Sarel van Vuuren, and
Ronald Cole (University of Colorado at Boulder)
- Improving Automatic Sentence Boundary Detection with Confusion Networks
- Dustin Hillard (University of Washington, SSLI),
Mari Ostendorf (University of Washington, SSLI), and
Andreas Stolcke (SRI/ICSI)
- A Comparison of Rule--Based and Statistical Methods for Semantic Language Modeling and Confidence Measurement
- Ruhi Srikaya,
Yuqing Gao, and
Michael Picheny (IBM T.J. Watson Research Center)
- Converting a Text into a Narration by an Animated Agent: Assigning Gestures to a Text
- Yukiko I. Nakano,
Masashi Okamoto,
Daisuke Kawahara,
Qing Li, and
Toyoaki Nishida (Japan Science and Technology Corporation)
- Parsing Conversational Speech Using Enhanced Segmentation
- Jeremy G. Kahn (University of Washington, SSLI),
Mari Ostendorf (University of Washington, SSLI), and
Ciprian Chelba (Microsoft Research)
- Competitive Self-Trained Pronoun Interpretation
- Andrew Kehler (UCSD Linguistics),
Douglas Appelt (SRI International),
Lara Taylor (UCSD Linguistics), and
Aleksandr Simma (UCSD Computer Science)
- Morphological Analysis for Statistical Machine Translation
- Young-Suk Lee (IBM T. J. Watson Research Center)
- Feature-based Pronunciation Modeling for Speech Recognition
- Karen Livescu and
James Glass (MIT CSAIL)
- Parsing Arguments of Nominalizations in English and Chinese
- Sameer S. Pradhan (University of Colorado at Boulder),
Honglin Sun (University of Colorado at Boulder),
Wayne Ward (University of Colorado at Boulder),
James H.Martin (University of Colorado at Boulder), and
Dan Jurafsky (Stanford University)
- Computational Linkuistics: word triggers across hyperlinks
- Dragomir Radev,
Hong Qi,
Adam Winkel, and
Daniel Tam (UMich)
- A speech-in list-out approach to spoken user interfaces
- Bhiksha Raj,
Peter Wolf,
Joe Woelfel,
Jan Van Gemert (Mitsubishi Electric Research Labs)
- Augmenting the kappa statistic to determine interannotator reliability for multiply labeled data points
- Andrew Rosenberg (Columbia University) and
Ed Binkowski (Hunter College)
- Correction Grammars for Error Handling in a Speech Dialog System
- Hirohiko Sagawa,
Teruko Mitamura,
Eric Nyberg (CMU/LTI)
- Nearly-Automated Metadata Hierarchy Creation
- Emilia Stoica and
Marti Hearst (University of California at Berkeley)
- A Unigram Orientation Model for Statistical Machine Translation
- Christoph Tillmann (IBM T. J. Watson Research Center)
Accepted Posters
- Language model adaptation with MAP estimation and the perceptron algorithm
- Michiel Bacchiani,
Brian Roark, and
Murat Saraclar (AT&T Research Labs)
- Confidence Estimation for Information Extraction
- Aron Culotta and
Andrew McCallum (University of Massachusetts at Amherst)
- Automatic Tagging of Arabic Text: From Raw Text to Base Phrase Chunks
- Mona Diab (Stanford University),
Kadri Hacioglu (University of Colorado at Boulder), and
Daniel Jurafsky (Stanford University)
- Enhancing Linguistically Oriented Automatic Keyword Extraction
- Anette Hulth (Stockholm University)
- MMR-based Feature Selection for Text Categorization
- Changki Lee and
Gary Geunbae Lee (Pohang University of Science & Technology)
- Prosody-based Topic Segmentation for Mandarin Broadcast News
- Gina-Anne Levow (University of Chicago)
- Automated Team Discourse Annotation and Performance Prediction Using LSA
- Melanie J. Martin and Peter W. Foltz (New Mexico State University)
- Direct Maximization of Average Precision by Hill-Climbing, with a Comparison to a Maximum Entropy Approach
- William Morgan,
Warren Greiff,
John Henderson (MITRE)
- Feature Selection for Trainable Multilingual Broadcast News Segmentation
- David D. Palmer,
Marc Reichman, and
Elyes Yaich (Virage)
- Example-based Rescoring of Statistical Machine Translation Output
- Michael Paul,
Eiichiro Sumita, and
Seiichi Yamamoto (ATR-SLT)
- Summarizing Email Threads
- Owen Rambow (Columbia University),
Lokesh Shrestha (Columbia University),
John Chen (Microsoft Research Asia), and
Christy Laurdisen (IBM)
- UI on the Fly: Generating a Multimodal User Interface
- David Reitter (Media Lab Europe),
Erin Panttaja (Media Lab Europe), and
Fred Cummins (University College Dublin)
- Context-based Speech Recognition Error Detection and Correction
- Arup Sarma and
David D. Palmer (Virage)
- Polarity sensitivity and evaluation order in type-logical grammar
- Chung-chieh Shan (Harvard University)
- HITIQA: A Data Driven Approach to Interactive Analytical Question Answering
- Sharon Small and Tomek Strzalkowski (SUNY Albany/ILS Institute)
- A Lexically-Driven Algorithm for Disfluency Detection
- Matthew Snover (UMD),
Bonnie Dorr (UMD), and
Rich Schwartz (BBN)
- Speech Graffiti vs. Natural Language: Assessing the User Experience
- Stefanie Tomko and
Roni Rosenfeld (CMU/LTI)
- An Empirical Study on Multiple LVCSR Model Combination by Machine Learning
- Takehito Utsuro (Kyoto University),
Yasuhiro Kodama (Sony),
Tomohiro Watanabe (Toyohashi University),
Hiromitsu Nishizaki (Yamanashi University), and
Seiichi Nakagawa (Toyohashi University)
- Using N-best list for Named Entity Recognition from Chinese Speech
- Lufeng Zhai (HKUST),
Pascale Fung (HKUST),
Richard Schwartz (BBN),
Marine Carpuat (HKUST), and
Dekai Wu (HKUST)
|
|
|
|
|
|