NAACL HLT 2009

Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics Short Papers

May 31 ­ June 5, 2009 Boulder, Colorado

Production and Manufacturing by Omnipress Inc. 2600 Anderson Street Madison, WI 53707 USA Sponsors: ˇ Rosetta Stone ˇ CNGL ˇ Microsoft Research ˇ Google ˇ AT&T ˇ Language Weaver ˇ J.D. Power ˇ IBM Research ˇ The Linguistic Data Consortium ˇ The Human Language Technology Center of Excellence at the Johns Hopkins University ˇ The Computational Language and Education Research Center at the University of Colorado at Boulder

c 2009 The Association for Computational Linguistics Order copies of this and other ACL proceedings from: Association for Computational Linguistics (ACL) 209 N. Eighth Street Stroudsburg, PA 18360 USA Tel: +1-570-476-8006 Fax: +1-570-476-0860 acl@aclweb.org

ISBN: 978-1-932432-42-8
ii

Table of Contents
Cohesive Constraints in A Beam Search Phrase-based Decoder Nguyen Bach, Stephan Vogel and Colin Cherry . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 Revisiting Optimal Decoding for Machine Translation IBM Model 4 Sebastian Riedel and James Clarke . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 Efficient Extraction of Oracle-best Translations from Hypergraphs Zhifei Li and Sanjeev Khudanpur . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 Semantic Roles for SMT: A Hybrid Two-Pass Model Dekai Wu and Pascale Fung . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 Comparison of Extended Lexicon Models in Search and Rescoring for SMT Saa Hasan and Hermann Ney . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 s A Simplex Armijo Downhill Algorithm for Optimizing Statistical Machine Translation Decoding Parameters Bing Zhao and Shengyuan Chen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 Translation Corpus Source and Size in Bilingual Retrieval Paul McNamee, James Mayfield and Charles Nicholas . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 Large-scale Computation of Distributional Similarities for Queries Enrique Alfonseca, Keith Hall and Silvana Hartmann . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 Text Categorization from Category Name via Lexical Reference Libby Barak, Ido Dagan and Eyal Shnarch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 Identifying Types of Claims in Online Customer Reviews Shilpa Arora, Mahesh Joshi and Carolyn P. Ros´ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 e Towards Automatic Image Region Annotation - Image Region Textual Coreference Resolution Emilia Apostolova and Dina Demner-Fushman . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 TESLA: A Tool for Annotating Geospatial Language Corpora Nate Blaylock, Bradley Swain and James Allen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 Modeling Dialogue Structure with Adjacency Pair Analysis and Hidden Markov Models Kristy Elizabeth Boyer, Robert Phillips, Eun Young Ha, Michael Wallis, Mladen Vouk and James Lester . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 Towards Natural Language Understanding of Partial Speech Recognition Results in Dialogue Systems Kenji Sagae, Gwen Christian, David DeVault and David Traum . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53 Spherical Discriminant Analysis in Semi-supervised Speaker Clustering Hao Tang, Stephen Chu and Thomas Huang . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57

iii

Learning Bayesian Networks for Semantic Frame Composition in a Spoken Dialog System Marie-Jean Meurs, Fabrice Lef` vre and Renato De Mori . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61 e Evaluation of a System for Noun Concepts Acquisition from Utterances about Images (SINCA) Using Daily Conversation Data Yuzu Uchida and Kenji Araki . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65 Web and Corpus Methods for Malay Count Classifier Prediction Jeremy Nicholson and Timothy Baldwin . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69 Minimum Bayes Risk Combination of Translation Hypotheses from Alternative Morphological Decompositions Adri` de Gispert, Sami Virpioja, Mikko Kurimo and William Byrne . . . . . . . . . . . . . . . . . . . . . . . . 73 a Generating Synthetic Children's Acoustic Models from Adult Models Andreas Hagen, Bryan Pellom and Kadri Hacioglu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77 Detecting Pitch Accents at the Word, Syllable and Vowel Level Andrew Rosenberg and Julia Hirschberg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81 Shallow Semantic Parsing for Spoken Language Understanding Bonaventura Coppola, Alessandro Moschitti and Giuseppe Riccardi . . . . . . . . . . . . . . . . . . . . . . . . 85 Automatic Agenda Graph Construction from Human-Human Dialogs using Clustering Method Cheongjae Lee, Sangkeun Jung, Kyungduk Kim and Gary Geunbae Lee . . . . . . . . . . . . . . . . . . . . 89 A Simple Sentence-Level Extraction Algorithm for Comparable Data Christoph Tillmann and Jian-ming Xu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 93 Learning Combination Features with L1 Regularization Daisuke Okanohara and Jun'ichi Tsujii . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 97 Multi-scale Personalization for Voice Search Applications Daniel Bola~ os, Geoffrey Zweig and Patrick Nguyen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 101 n The Importance of Sub-Utterance Prosody in Predicting Level of Certainty Heather Pon-Barry and Stuart Shieber . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 105 Using Integer Linear Programming for Detecting Speech Disfluencies Kallirroi Georgila . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 109 Contrastive Summarization: An Experiment with Consumer Reviews Kevin Lerman and Ryan McDonald . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 113 Topic Identification Using Wikipedia Graph Centrality Kino Coursey and Rada Mihalcea . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 117 Extracting Bilingual Dictionary from Comparable Corpora with Dependency Heterogeneity Kun Yu and Jun'ichi Tsujii . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 121

iv

Domain Adaptation with Artificial Data for Semantic Parsing of Speech Lonneke van der Plas, James Henderson and Paola Merlo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 125 Extending Pronunciation Lexicons via Non-phonemic Respellings Lucian Galescu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 129 A Speech Understanding Framework that Uses Multiple Language Models and Multiple Understanding Models Masaki Katsumaru, Mikio Nakano, Kazunori Komatani, Kotaro Funakoshi, Tetsuya Ogata and Hiroshi G. Okuno . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 133 Taking into Account the Differences between Actively and Passively Acquired Data: The Case of Active Learning with Support Vector Machines for Imbalanced Datasets Michael Bloodgood and Vijay Shanker . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 137 Faster MT Decoding Through Pervasive Laziness Michael Pust and Kevin Knight . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 141 Evaluating the Syntactic Transformations in Gold Standard Corpora for Statistical Sentence Compression Naman K. Gupta, Sourish Chaudhuri and Carolyn P. Ros´ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 145 e Incremental Adaptation of Speech-to-Speech Translation Nguyen Bach, Roger Hsiao, Matthias Eck, Paisarn Charoenpornsawat, Stephan Vogel, Tanja Schultz, Ian Lane, Alex Waibel and Alan Black . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 149 Name Perplexity Octavian Popescu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 153 Answer Credibility: A Language Modeling Approach to Answer Validation Protima Banerjee and Hyoil Han . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 157 Exploiting Named Entity Classes in CCG Surface Realization Rajakrishnan Rajkumar, Michael White and Dominic Espinosa . . . . . . . . . . . . . . . . . . . . . . . . . . . 161 Search Engine Adaptation by Feedback Control Adjustment for Time-sensitive Query Ruiqiang Zhang, Yi Chang, Zhaohui Zheng, Donald Metzler and Jian-yun Nie . . . . . . . . . . . . . . 165 A Local Tree Alignment-based Soft Pattern Matching Approach for Information Extraction Seokhwan Kim, Minwoo Jeong and Gary Geunbae Lee . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 169 Classifying Factored Genres with Part-of-Speech Histograms Sergey Feldman, Marius Marin, Julie Medero and Mari Ostendorf . . . . . . . . . . . . . . . . . . . . . . . . . 173 Towards Effective Sentence Simplification for Automatic Processing of Biomedical Text Siddhartha Jonnalagadda, Luis Tari, J¨ rg Hakenberg, Chitta Baral and Graciela Gonzalez . . . . 177 o Improving SCL Model for Sentiment-Transfer Learning Songbo Tan and Xueqi Cheng . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 181

v

MICA: A Probabilistic Dependency Parser Based on Tree Insertion Grammars (Application Note) Srinivas Bangalore, Pierre Boullier, Alexis Nasr, Owen Rambow and Beno^t Sagot . . . . . . . . . . 185 i Lexical and Syntactic Adaptation and Their Impact in Deployed Spoken Dialog Systems Svetlana Stoyanchev and Amanda Stent . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 189 Analysing Recognition Errors in Unlimited-Vocabulary Speech Recognition Teemu Hirsim¨ ki and Mikko Kurimo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 193 a The independence of dimensions in multidimensional dialogue act annotation Volha Petukhova and Harry Bunt . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 197 Improving Coreference Resolution by Using Conversational Metadata Xiaoqiang Luo, Radu Florian and Todd Ward . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 201 Using N-gram based Features for Machine Translation System Combination Yong Zhao and Xiaodong He . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 205 Language Specific Issue and Feature Exploration in Chinese Event Extraction Zheng Chen and Heng Ji . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 209 Improving A Simple Bigram HMM Part-of-Speech Tagger by Latent Annotation and Self-Training Zhongqiang Huang, Vladimir Eidelman and Mary Harper . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 213 Statistical Post-Editing of a Rule-Based Machine Translation System Antonio-L. Lagarda, Vicent Alabau, Francisco Casacuberta, Roberto Silva and Enrique D´az-dei Lia~ o . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 217 n On the Importance of Pivot Language Selection for Statistical Machine Translation Michael Paul, Hirofumi Yamamoto, Eiichiro Sumita and Satoshi Nakamura . . . . . . . . . . . . . . . . 221 Tree Linearization in English: Improving Language Model Based Approaches Katja Filippova and Michael Strube . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 225 Determining the position of adverbial phrases in English Huayan Zhong and Amanda Stent . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 229 Estimating and Exploiting the Entropy of Sense Distributions Peng Jin, Diana McCarthy, Rob Koeling and John Carroll . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 233 Semantic Classification with WordNet Kernels ´ e Diarmuid O S´ aghdha . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 237 Sentence Boundary Detection and the Problem with the U.S. Dan Gillick . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 241 Quadratic Features and Deep Architectures for Chunking Joseph Turian, James Bergstra and Yoshua Bengio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 245

vi

Active Zipfian Sampling for Statistical Parser Training Onur Cobano lu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 249 ¸ g Combining Constituent Parsers Victoria Fossum and Kevin Knight . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 253 Recognising the Predicate-argument Structure of Tagalog Meladel Mistica and Timothy Baldwin . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 257 Reverse Revision and Linear Tree Combination for Dependency Parsing Giuseppe Attardi and Felice Dell'Orletta . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 261 Anchored Speech Recognition for Question Answering Sibel Yaman, Gokan Tur, Dimitra Vergyri, Dilek Hakkani-Tur, Mary Harper and Wen Wang . 265 Score Distribution Based Term Specific Thresholding for Spoken Term Detection Dogan Can and Murat Saraclar . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 269 Automatic Chinese Abbreviation Generation Using Conditional Random Field Dong Yang, Yi-Cheng Pan and Sadaoki Furui . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 273 Fast decoding for open vocabulary spoken term detection Bhuvana Ramabhadran, Abhinav Sethy, Jonathan Mamou, Brian Kingsbury and Upendra Chaudhari . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 277 Tightly coupling Speech Recognition and Search Taniya Mishra and Srinivas Bangalore . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 281

vii

Conference Program Overview
Monday, June 1, 2009 9:00­10:10 10:40­11:20 Plenary Session ­ Invited Talk by Antonio Torralba: Understanding Visual Scenes Session 1A: Semantics Session 1B: Multilingual Processing / Morphology and Phonology Session 1C: Syntax and Parsing Student Research Workshop Session 1 Short Paper Presentations: Session 2A: Machine Translation Session 2B: Information Retrieval / Information Extraction / Sentiment Session 2C: Dialog / Speech / Semantics Student Research Workshop Session 2 Session 3A: Machine Translation Session 3B: Semantics Session 3C: Information Retrieval Student Research Workshop Session 3 Poster and Demo Session Student Research Workshop Poster Session

2:00­3:30

4:00­5:40

6:30­9:30

Tuesday, June 2, 2009 9:00-10:10 10:10­11:40 Plenary Session: Paper Award Presentations Session 4A: Machine Translation Session 4B: Sentiment Analysis / Information Extraction Session 4C: Machine Learning / Morphology and Phonology Short Paper Presentations: Session 5A: Machine Translation / Generation / Semantics Session 5B: Machine Learning / Syntax Session 5C: SPECIAL SESSION ­ Speech Indexing and Retrieval Session 6A: Syntax and Parsing Session 6B: Discourse and Summarization Session 6C: Spoken Language Systems

2:00­3:30

4:00­5:15

ix

Wednesday, June 3, 2009 9:00­10:10 Plenary Session ­ Invited Talk by Dan Jurafsky: Ketchup, Espresso, and Chocolate Chip Cookies: Travels in the Language of Food Session 7A: Machine Translation Session 7B: Speech Recognition and Language Modeling Session 7C: Sentiment Analysis Panel Discussion: Emerging Application Areas in Computational Linguistics NAACL Business Meeting Session 8A: Large-scale NLP Session 8B: Syntax and Parsing Session 8C: Discourse and Summarization Session 9A: Machine Learning Session 9B: Dialog Systems Session 9C: Syntax and Parsing

10:40­12:20

12:40-1:40 1:40­2:30 2:30­3:45

4:15­5:30

x

Conference Program
Monday, June 1, 2009 Plenary Session 9:00­10:10 Welcome and Invited Talk: Understanding Visual Scenes Antonio Torralba Break Session 1A: Semantics Note: all full papers are located in the Main volume of the proceedings 10:40­11:05 Subjectivity Recognition on Word Senses via Semi-supervised Mincuts Fangzhong Su and Katja Markert Integrating Knowledge for Subjectivity Sense Labeling Yaw Gyamfi, Janyce Wiebe, Rada Mihalcea and Cem Akkaya A Study on Similarity and Relatedness Using Distributional and WordNet-based Approaches Eneko Agirre, Enrique Alfonseca, Keith Hall, Jana Kravalova, Marius Pasca and Aitor Soroa A Fully Unsupervised Word Sense Disambiguation Method Using Dependency Knowledge Ping Chen, Wei Ding, Chris Bowes and David Brown Session 1B: Multilingual Processing / Morphology and Phonology 10:40­11:05 Learning Phoneme Mappings for Transliteration without Parallel Data Sujith Ravi and Kevin Knight A Corpus-Based Approach for the Prediction of Language Impairment in Monolingual English and Spanish-English Bilingual Children Keyur Gabani, Melissa Sherman, Thamar Solorio, Yang Liu, Lisa Bedore and Elizabeth Pe~ a n A Discriminative Latent Variable Chinese Segmenter with Hybrid Word/Character Information Xu Sun, Yaozhong Zhang, Takuya Matsuzaki, Yoshimasa Tsuruoka and Jun'ichi Tsujii Improved Reconstruction of Protolanguage Word Forms Alexandre Bouchard-C^ t´ , Thomas L. Griffiths and Dan Klein oe

10:10­10:40

11:05­11:30

11:30­11:55

11:55­12:20

11:05­11:30

11:30­11:55

11:55­12:20

xi

Monday, June 1, 2009 (continued) Session 1C: Syntax and Parsing 10:40­11:05 Shared Logistic Normal Distributions for Soft Parameter Tying in Unsupervised Grammar Induction Shay Cohen and Noah A. Smith Adding More Languages Improves Unsupervised Multilingual Part-of-Speech Tagging: a Bayesian Non-Parametric Approach Benjamin Snyder, Tahira Naseem, Jacob Eisenstein and Regina Barzilay Efficiently Parsable Extensions to Tree-Local Multicomponent TAG Rebecca Nesson and Stuart Shieber Improving Unsupervised Dependency Parsing with Richer Contexts and Smoothing William P. Headden III, Mark Johnson and David McClosky Student Research Workshop Session 1: Note: all student research workshop papers are located in the Companion volume of the proceedings 10:40­11:10 Classifier Combination Techniques Applied to Coreference Resolution Smita Vemulapalli, Xiaoqiang Luo, John F. Pitrelli and Imed Zitouni Solving the "Who's Mark Johnson Puzzle": Information Extraction Based Cross Document Coreference Jian Huang, Sarah M. Taylor, Jonathan L. Smith, Konstantinos A. Fotiadis and C. Lee Giles Exploring Topic Continuation Follow-up Questions using Machine Learning Manuel Kirschner and Raffaella Bernardi Lunch Break

11:05­11:30

11:30­11:55

11:55­12:20

11:15­11:45

11:50­12:20

12:20­2:00

xii

Monday, June 1, 2009 (continued) Session 2A: Short Paper Presentations: Machine Translation 2:00­2:15 Cohesive Constraints in A Beam Search Phrase-based Decoder Nguyen Bach, Stephan Vogel and Colin Cherry Revisiting Optimal Decoding for Machine Translation IBM Model 4 Sebastian Riedel and James Clarke Efficient Extraction of Oracle-best Translations from Hypergraphs Zhifei Li and Sanjeev Khudanpur Semantic Roles for SMT: A Hybrid Two-Pass Model Dekai Wu and Pascale Fung Comparison of Extended Lexicon Models in Search and Rescoring for SMT Saa Hasan and Hermann Ney s A Simplex Armijo Downhill Algorithm for Optimizing Statistical Machine Translation Decoding Parameters Bing Zhao and Shengyuan Chen Session 2B: Short Paper Presentations: Information Retrieval / Information Extraction / Sentiment 2:00­2:15 Translation Corpus Source and Size in Bilingual Retrieval Paul McNamee, James Mayfield and Charles Nicholas Large-scale Computation of Distributional Similarities for Queries Enrique Alfonseca, Keith Hall and Silvana Hartmann Text Categorization from Category Name via Lexical Reference Libby Barak, Ido Dagan and Eyal Shnarch Identifying Types of Claims in Online Customer Reviews Shilpa Arora, Mahesh Joshi and Carolyn P. Ros´ e Towards Automatic Image Region Annotation - Image Region Textual Coreference Resolution Emilia Apostolova and Dina Demner-Fushman

2:15­2:30

2:30­2:45

2:45­3:00

3:00­3:15

3:15­3:30

2:15­2:30

2:30­2:45

2:45­3:00

3:00­3:15

xiii

Monday, June 1, 2009 (continued) 3:15­3:30 TESLA: A Tool for Annotating Geospatial Language Corpora Nate Blaylock, Bradley Swain and James Allen Session 2C: Short Paper Presentations: Dialog / Speech / Semantics 2:00­2:15 Modeling Dialogue Structure with Adjacency Pair Analysis and Hidden Markov Models Kristy Elizabeth Boyer, Robert Phillips, Eun Young Ha, Michael Wallis, Mladen Vouk and James Lester Towards Natural Language Understanding of Partial Speech Recognition Results in Dialogue Systems Kenji Sagae, Gwen Christian, David DeVault and David Traum Spherical Discriminant Analysis in Semi-supervised Speaker Clustering Hao Tang, Stephen Chu and Thomas Huang Learning Bayesian Networks for Semantic Frame Composition in a Spoken Dialog System Marie-Jean Meurs, Fabrice Lef` vre and Renato De Mori e Evaluation of a System for Noun Concepts Acquisition from Utterances about Images (SINCA) Using Daily Conversation Data Yuzu Uchida and Kenji Araki Web and Corpus Methods for Malay Count Classifier Prediction Jeremy Nicholson and Timothy Baldwin

2:15­2:30

2:30­2:45

2:45­3:00

3:00­3:15

3:15­3:30

xiv

Monday, June 1, 2009 (continued) Student Research Workshop Session 2 Note: all student research workshop papers are located in the Companion volume of the proceedings 2:00­2:30 Sentence Realisation from Bag of Words with Dependency Constraints Karthik Gali and Sriram Venkatapathy Using Language Modeling to Select Useful Annotation Data Dmitriy Dligach and Martha Palmer Break Session 3A: Machine Translation 4:00­4:25 Context-Dependent Alignment Models for Statistical Machine Translation Jamie Brunning, Adri` de Gispert and William Byrne a Graph-based Learning for Statistical Machine Translation Andrei Alexandrescu and Katrin Kirchhoff Intersecting Multilingual Data for Faster and Better Statistical Translations Yu Chen, Martin Kay and Andreas Eisele No Presentation Session 3B: Semantics 4:00­4:25 Without a 'doubt'? Unsupervised Discovery of Downward-Entailing Operators Cristian Danescu-Niculescu-Mizil, Lillian Lee and Richard Ducott The Role of Implicit Argumentation in Nominal SRL Matthew Gerber, Joyce Chai and Adam Meyers Jointly Identifying Predicates, Arguments and Senses using Markov Logic Ivan Meza-Ruiz and Sebastian Riedel Structured Generative Models for Unsupervised Named-Entity Clustering Micha Elsner, Eugene Charniak and Mark Johnson

2:35­3:05

3:30­4:00

4:25­4:50

4:50­5:15

5:15­5:40

4:25­4:50

4:50­5:15

5:15­5:40

xv

Monday, June 1, 2009 (continued) Session 3C: Information Retrieval 4:00­4:25 Hierarchical Dirichlet Trees for Information Retrieval Gholamreza Haffari and Yee Whye Teh Phrase-Based Query Degradation Modeling for Vocabulary-Independent Ranked Utterance Retrieval J. Scott Olsson and Douglas W. Oard Japanese Query Alteration Based on Lexical Semantic Similarity Masato Hagiwara and Hisami Suzuki Context-based Message Expansion for Disentanglement of Interleaved Text Conversations Lidan Wang and Douglas Oard Student Research Workshop Session 3 Note: all student research workshop papers are located in the Companion volume of the proceedings 4:00­4:30 Pronunciation Modeling in Spelling Correction for Writers of English as a Foreign Language Adriane Boyd Building a Semantic Lexicon of English Nouns via Bootstrapping Ting Qian, Benjamin Van Durme and Lenhart Schubert Multiple Word Alignment with Profile Hidden Markov Models Aditya Bhargava and Grzegorz Kondrak Poster and Demo Session Note: all demo abstracts are located in the Companion volume of the proceedings Minimum Bayes Risk Combination of Translation Hypotheses from Alternative Morphological Decompositions Adri` de Gispert, Sami Virpioja, Mikko Kurimo and William Byrne a Generating Synthetic Children's Acoustic Models from Adult Models Andreas Hagen, Bryan Pellom and Kadri Hacioglu

4:25­4:50

4:50­5:15

5:15­5:40

4:35­5:05

5:10­5:40

6:30­9:30

xvi

Monday, June 1, 2009 (continued) Detecting Pitch Accents at the Word, Syllable and Vowel Level Andrew Rosenberg and Julia Hirschberg Shallow Semantic Parsing for Spoken Language Understanding Bonaventura Coppola, Alessandro Moschitti and Giuseppe Riccardi Automatic Agenda Graph Construction from Human-Human Dialogs using Clustering Method Cheongjae Lee, Sangkeun Jung, Kyungduk Kim and Gary Geunbae Lee A Simple Sentence-Level Extraction Algorithm for Comparable Data Christoph Tillmann and Jian-ming Xu Learning Combination Features with L1 Regularization Daisuke Okanohara and Jun'ichi Tsujii Multi-scale Personalization for Voice Search Applications Daniel Bola~ os, Geoffrey Zweig and Patrick Nguyen n The Importance of Sub-Utterance Prosody in Predicting Level of Certainty Heather Pon-Barry and Stuart Shieber Using Integer Linear Programming for Detecting Speech Disfluencies Kallirroi Georgila Contrastive Summarization: An Experiment with Consumer Reviews Kevin Lerman and Ryan McDonald Topic Identification Using Wikipedia Graph Centrality Kino Coursey and Rada Mihalcea Extracting Bilingual Dictionary from Comparable Corpora with Dependency Heterogeneity Kun Yu and Jun'ichi Tsujii Domain Adaptation with Artificial Data for Semantic Parsing of Speech Lonneke van der Plas, James Henderson and Paola Merlo

xvii

Monday, June 1, 2009 (continued) Extending Pronunciation Lexicons via Non-phonemic Respellings Lucian Galescu A Speech Understanding Framework that Uses Multiple Language Models and Multiple Understanding Models Masaki Katsumaru, Mikio Nakano, Kazunori Komatani, Kotaro Funakoshi, Tetsuya Ogata and Hiroshi G. Okuno Taking into Account the Differences between Actively and Passively Acquired Data: The Case of Active Learning with Support Vector Machines for Imbalanced Datasets Michael Bloodgood and Vijay Shanker Faster MT Decoding Through Pervasive Laziness Michael Pust and Kevin Knight Evaluating the Syntactic Transformations in Gold Standard Corpora for Statistical Sentence Compression Naman K. Gupta, Sourish Chaudhuri and Carolyn P. Ros´ e Incremental Adaptation of Speech-to-Speech Translation Nguyen Bach, Roger Hsiao, Matthias Eck, Paisarn Charoenpornsawat, Stephan Vogel, Tanja Schultz, Ian Lane, Alex Waibel and Alan Black Name Perplexity Octavian Popescu Answer Credibility: A Language Modeling Approach to Answer Validation Protima Banerjee and Hyoil Han Exploiting Named Entity Classes in CCG Surface Realization Rajakrishnan Rajkumar, Michael White and Dominic Espinosa Search Engine Adaptation by Feedback Control Adjustment for Time-sensitive Query Ruiqiang Zhang, Yi Chang, Zhaohui Zheng, Donald Metzler and Jian-yun Nie A Local Tree Alignment-based Soft Pattern Matching Approach for Information Extraction Seokhwan Kim, Minwoo Jeong and Gary Geunbae Lee Classifying Factored Genres with Part-of-Speech Histograms Sergey Feldman, Marius Marin, Julie Medero and Mari Ostendorf

xviii

Monday, June 1, 2009 (continued) Towards Effective Sentence Simplification for Automatic Processing of Biomedical Text Siddhartha Jonnalagadda, Luis Tari, J¨ rg Hakenberg, Chitta Baral and Graciela Gonzalez o Improving SCL Model for Sentiment-Transfer Learning Songbo Tan and Xueqi Cheng MICA: A Probabilistic Dependency Parser Based on Tree Insertion Grammars (Application Note) Srinivas Bangalore, Pierre Boullier, Alexis Nasr, Owen Rambow and Beno^t Sagot i Lexical and Syntactic Adaptation and Their Impact in Deployed Spoken Dialog Systems Svetlana Stoyanchev and Amanda Stent Analysing Recognition Errors in Unlimited-Vocabulary Speech Recognition Teemu Hirsim¨ ki and Mikko Kurimo a The independence of dimensions in multidimensional dialogue act annotation Volha Petukhova and Harry Bunt Improving Coreference Resolution by Using Conversational Metadata Xiaoqiang Luo, Radu Florian and Todd Ward Using N-gram based Features for Machine Translation System Combination Yong Zhao and Xiaodong He Language Specific Issue and Feature Exploration in Chinese Event Extraction Zheng Chen and Heng Ji Improving A Simple Bigram HMM Part-of-Speech Tagger by Latent Annotation and SelfTraining Zhongqiang Huang, Vladimir Eidelman and Mary Harper 6:30­9:30 Student Research Workshop Poster Session Note: all student research workshop papers are located in the Companion volume of the proceedings Also: All papers presented in the morning and afternoon sessions of the student research workshop will also be shown as posters.

xix

Monday, June 1, 2009 (continued) Using Emotion to Gain Rapport in a Spoken Dialog System Jaime Acosta Interactive Annotation Learning with Indirect Feature Voting Shilpa Arora and Eric Nyberg Loss-Sensitive Discriminative Training of Machine Transliteration Models Kedar Bellare, Koby Crammer and Dayne Freitag Syntactic Tree-based Relation Extraction Using a Generalization of Collins and Duffy Convolution Tree Kernel Mahdy Khayyamian, Seyed Abolghasem Mirroshandel and Hassan Abolhassani Towards Building a Competitive Opinion Summarization System: Challenges and Keys Elena Lloret, Alexandra Balahur, Manuel Palomar and Andres Montoyo Domain-Independent Shallow Sentence Ordering Thade Nahnsen Towards Unsupervised Recognition of Dialogue Acts Nicole Novielli and Carlo Strapparava Modeling Letter-to-Phoneme Conversion as a Phrase Based Statistical Machine Translation Problem with Minimum Error Rate Training Taraka Rama, Anil Kumar Singh and Sudheer Kolachina Disambiguation of Preposition Sense Using Linguistically Motivated Features Stephen Tratz and Dirk Hovy

xx

Tuesday, June 2, 2009 Plenary Session 9:00­9:10 9:10­9:40 Paper Awards Unsupervised Morphological Segmentation with Log-Linear Models Hoifung Poon, Colin Cherry and Kristina Toutanova 11,001 New Features for Statistical Machine Translation David Chiang, Kevin Knight and Wei Wang Break Session 4A: Machine Translation 10:10­10:35 Efficient Parsing for Transducer Grammars John DeNero, Mohit Bansal, Adam Pauls and Dan Klein Preference Grammars: Softening Syntactic Constraints to Improve Statistical Machine Translation Ashish Venugopal, Andreas Zollmann, Noah Smith and Stephan Vogel Using a Dependency Parser to Improve SMT for Subject-Object-Verb Languages Peng Xu, Jaeho Kang, Michael Ringgaard and Franz Och Learning Bilingual Linguistic Reordering Model for Statistical Machine Translation Han-Bin Chen, Jian-Cheng Wu and Jason S. Chang

9:40­10:10

10:10-10:40

10:35­10:50

10:50­11:15

11:15­11:40

xxi

Tuesday, June 2, 2009 (continued) Session 4B: Sentiment Analysis / Information Extraction 10:10­10:35 May All Your Wishes Come True: A Study of Wishes and How to Recognize Them Andrew Goldberg, Nathanael Fillmore, David Andrzejewski, Zhiting Xu, Bryan Gibson and Xiaojin Zhu Predicting Risk from Financial Reports with Regression Shimon Kogan, Dimitry Levin, Bryan R. Routledge, Jacob S. Sagi and Noah A. Smith Domain Adaptation with Latent Semantic Association for Named Entity Recognition Honglei Guo, Huijia Zhu, Zhili Guo, Xiaoxun Zhang, Xian Wu and Zhong Su Semi-Automatic Entity Set Refinement Vishnu Vyas and Patrick Pantel Session 4C: Machine Learning / Morphology and Phonology 10:10­10:35 Unsupervised Constraint Driven Learning For Transliteration Discovery Ming-Wei Chang, Dan Goldwasser, Dan Roth and Yuancheng Tu On the Syllabification of Phonemes Susan Bartlett, Grzegorz Kondrak and Colin Cherry Improving nonparameteric Bayesian inference: experiments on unsupervised word segmentation with adaptor grammars Mark Johnson and Sharon Goldwater No Presentation Lunch Break

10:35­10:50

10:50­11:15

11:15­11:40

10:35­10:50

10:50­11:15

11:15­11:40 12:20­2:00

xxii

Tuesday, June 2, 2009 (continued) Session 5A: Short Paper Presentations: Machine Translation / Generation / Semantics 2:00­2:15 Statistical Post-Editing of a Rule-Based Machine Translation System Antonio-L. Lagarda, Vicent Alabau, Francisco Casacuberta, Roberto Silva and Enrique D´az-de-Lia~ o i n On the Importance of Pivot Language Selection for Statistical Machine Translation Michael Paul, Hirofumi Yamamoto, Eiichiro Sumita and Satoshi Nakamura Tree Linearization in English: Improving Language Model Based Approaches Katja Filippova and Michael Strube Determining the position of adverbial phrases in English Huayan Zhong and Amanda Stent Estimating and Exploiting the Entropy of Sense Distributions Peng Jin, Diana McCarthy, Rob Koeling and John Carroll Semantic Classification with WordNet Kernels ´ e Diarmuid O S´ aghdha Session 5B: Short Paper Presentations: Machine Learning / Syntax 2:00­2:15 Sentence Boundary Detection and the Problem with the U.S. Dan Gillick Quadratic Features and Deep Architectures for Chunking Joseph Turian, James Bergstra and Yoshua Bengio Active Zipfian Sampling for Statistical Parser Training Onur Cobano lu ¸ g Combining Constituent Parsers Victoria Fossum and Kevin Knight Recognising the Predicate-argument Structure of Tagalog Meladel Mistica and Timothy Baldwin

2:15­2:30

2:30­2:45

2:45­3:00

3:00­3:15

3:15­3:30

2:15­2:30

2:30­2:45

2:45­3:00

3:00­3:15

xxiii

Tuesday, June 2, 2009 (continued) 3:15­3:30 Reverse Revision and Linear Tree Combination for Dependency Parsing Giuseppe Attardi and Felice Dell'Orletta Session 5C: Short Paper Presentations: SPECIAL SESSION ­ Speech Indexing and Retrieval 2:00­2:15 2:15­2:30 Introduction to the Special Session on Speech Indexing and Retrieval Anchored Speech Recognition for Question Answering Sibel Yaman, Gokan Tur, Dimitra Vergyri, Dilek Hakkani-Tur, Mary Harper and Wen Wang Score Distribution Based Term Specific Thresholding for Spoken Term Detection Dogan Can and Murat Saraclar Automatic Chinese Abbreviation Generation Using Conditional Random Field Dong Yang, Yi-Cheng Pan and Sadaoki Furui Fast decoding for open vocabulary spoken term detection Bhuvana Ramabhadran, Abhinav Sethy, Jonathan Mamou, Brian Kingsbury and Upendra Chaudhari Tightly coupling Speech Recognition and Search Taniya Mishra and Srinivas Bangalore Break Session 6A: Syntax and Parsing 4:00­4:25 Joint Parsing and Named Entity Recognition Jenny Rose Finkel and Christopher D. Manning Minimal-length linearizations for mildly context-sensitive dependency trees Y. Albert Park and Roger Levy Positive Results for Parsing with a Bounded Stack using a Model-Based Right-Corner Transform William Schuler

2:30­2:45

2:45­3:00

3:00­3:15

3:15­3:30

3:30­4:00

4:25­4:50

4:50­5:15

xxiv

Tuesday, June 2, 2009 (continued) Session 6B: Discourse and Summarization 4:00­4:25 Hierarchical Text Segmentation from Multi-Scale Lexical Cohesion Jacob Eisenstein Exploring Content Models for Multi-Document Summarization Aria Haghighi and Lucy Vanderwende Global Models of Document Structure using Latent Permutations Harr Chen, S.R.K. Branavan, Regina Barzilay and David R. Karger Session 6C: Spoken Language Systems 4:00­4:25 Assessing and Improving the Performance of Speech Recognition for Incremental Systems Timo Baumann, Michaela Atterer and David Schlangen Geo-Centric Language Models for Local Business Voice Search Amanda Stent, Ilija Zeljkovic, Diamantino Caseiro and Jay Wilpon Improving the Arabic Pronunciation Dictionary for Phone and Word Recognition with Linguistically-Based Pronunciation Rules Fadi Biadsy, Nizar Habash and Julia Hirschberg

4:25­4:50

4:50­5:15

4:25­4:50

4:50­5:15

Wednesday, June 3, 2009 Plenary Session 9:00­10:10 Invited Talk: Ketchup, Espresso, and Chocolate Chip Cookies: Travels in the Language of Food Dan Jurafsky Break

10:10­10:40

xxv

Wednesday, June 3, 2009 (continued) Session 7A: Machine Translation 10:40­11:05 Using a maximum entropy model to build segmentation lattices for MT Chris Dyer Active Learning for Statistical Phrase-based Machine Translation Gholamreza Haffari, Maxim Roy and Anoop Sarkar Semi-Supervised Lexicon Mining from Parenthetical Expressions in Monolingual Web Pages Xianchao Wu, Naoaki Okazaki and Jun'ichi Tsujii Hierarchical Phrase-Based Translation with Weighted Finite State Transducers Gonzalo Iglesias, Adri` de Gispert, Eduardo R. Banga and William Byrne a Session 7B: Speech Recognition and Language Modeling 10:40­11:05 Improved pronunciation features for construct-driven assessment of non-native spontaneous speech Lei Chen, Klaus Zechner and Xiaoming Xi Performance Prediction for Exponential Language Models Stanley Chen Tied-Mixture Language Modeling in Continuous Space Ruhi Sarikaya, Mohamed Afify and Brian Kingsbury Shrinking Exponential Language Models Stanley Chen

11:05­11:30

11:30­11:55

11:55­12:20

11:05­11:30

11:30­11:55

11:55­12:20

xxvi

Wednesday, June 3, 2009 (continued) Session 7C: Sentiment Analysis 10:40­11:05 Predicting Response to Political Blog Posts with Topic Models Tae Yano, William W. Cohen and Noah A. Smith An Iterative Reinforcement Approach for Fine-Grained Opinion Mining Weifu Du and Songbo Tan For a few dollars less: Identifying review pages sans human labels Luciano Barbosa, Ravi Kumar, Bo Pang and Andrew Tomkins More than Words: Syntactic Packaging and Implicit Sentiment Stephan Greene and Philip Resnik Lunch Break Panel Discussion: Emerging Application Areas in Computational Linguistics Chaired by Bill Dolan, Microsoft Panelists: Jill Burstein, Educational Testing Service; Joel Tetreault, Educational Testing Service; Patrick Pantel, Yahoo; Andy Hickl, Language Computer Corporation + Swingly NAACL Business Meeting Session 8A: Large-scale NLP 2:30­2:55 Streaming for large scale NLP: Language Modeling Amit Goyal, Hal Daume III and Suresh Venkatasubramanian The Effect of Corpus Size on Case Frame Acquisition for Discourse Analysis Ryohei Sasano, Daisuke Kawahara and Sadao Kurohashi Semantic-based Estimation of Term Informativeness Kirill Kireyev

11:05­11:30

11:30­11:55

11:55­12:20

12:20­1:40 12:40-1:40

1:40­2:30

2:55­3:20

3:20­3:45

xxvii

Wednesday, June 3, 2009 (continued) Session 8B: Syntax and Parsing 2:30­2:55 Optimal Reduction of Rule Length in Linear Context-Free Rewriting Systems Carlos G´ mez-Rodr´guez, Marco Kuhlmann, Giorgio Satta and David Weir o i Inducing Compact but Accurate Tree-Substitution Grammars Trevor Cohn, Sharon Goldwater and Phil Blunsom Hierarchical Search for Parsing Adam Pauls and Dan Klein Session 8C: Discourse and Summarization 2:30­2:55 An effective Discourse Parser that uses Rich Linguistic Information Rajen Subba and Barbara Di Eugenio Graph-Cut-Based Anaphoricity Determination for Coreference Resolution Vincent Ng Using Citations to Generate surveys of Scientific Paradigms Saif Mohammad, Bonnie Dorr, Melissa Egan, Ahmed Hassan, Pradeep Muthukrishan, Vahed Qazvinian, Dragomir Radev and David Zajic Break Session 9A: Machine Learning 4:15­4:40 Non-Parametric Bayesian Areal Linguistics Hal Daume III Hierarchical Bayesian Domain Adaptation Jenny Rose Finkel and Christopher D. Manning Online EM for Unsupervised Models Percy Liang and Dan Klein

2:55­3:20

3:20­3:45

2:55­3:20

3:20­3:45

3:45­4:15

4:40­5:05

5:05­5:30

xxviii

Wednesday, June 3, 2009 (continued) Session 9B: Dialog Systems 4:15­4:40 Unsupervised Approaches for Automatic Keyword Extraction Using Meeting Transcripts Feifan Liu, Deana Pennell, Fei Liu and Yang Liu A Finite-State Turn-Taking Model for Spoken Dialog Systems Antoine Raux and Maxine Eskenazi Extracting Social Meaning: Identifying Interactional Style in Spoken Conversation Dan Jurafsky, Rajesh Ranganath and Dan McFarland Session 9C: Syntax and Parsing 4:15­4:40 Linear Complexity Context-Free Parsing Pipelines via Chart Constraints Brian Roark and Kristy Hollingshead Improved Syntactic Models for Parsing Speech with Repairs Tim Miller A model of local coherence effects in human sentence processing as consequences of updates from bottom-up prior to posterior beliefs Klinton Bicknell and Roger Levy

4:40­5:05

5:05­5:30

4:40­5:05

5:05­5:30

xxix