NAACL HLT 2009

Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics Proceedings of the Student Research Workshop and Doctoral Consortium
Anoop Sarkar, Carolyn Rose, Svetlana Stoyanchev, Ulrich Germann and Chirag Shah Chairs

June 1, 2009 Boulder, Colorado

Production and Manufacturing by Omnipress Inc. 2600 Anderson Street Madison, WI 53707 USA

We gratefully acknowledge financial support from the U.S. National Science Foundation.

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

Preface
Welcome to the NAACL HLT 2009 Student Research Workshop and Doctoral Consortium! We are pleased to continue this established tradition at ACL conferences. The Student Research Workshop and Doctoral Consortium provides a venue for student researchers in Computational Linguistics, Natural Language Processing, and Human Language Technologies to present their work and receive feedback from the community. Unlike regular conference sessions, the workshop welcomes work in progress. In the tradition of previous doctoral consortia, we recruited expert panelists to provide a brief commentary on each oral presentation. We hope that as a result of this workshop, the student participants are able to obtain exposure to the NAACL community and that it helps with their future careers in this field. This year we received 29 submissions from 11 countries. With a strong program committee of 86 reviewers, from advanced graduate students to senior experts in their field, we were able to keep the individual reviewing load light and assign to each paper a team of three to six reviewers. Most papers were reviewed by two student reviewers and two established researchers. We would like to thank the reviewers for understanding the spirit of the workshop and giving careful and constructive reviews. We hope their comments will be helpful to all the students who submitted their work. A grant from the U.S. National Science Foundation enables us to provide financial support to all presenters to assist them in their travel to and attendance of the conference. We gratefully acknowledge this generous contribution. Finally, we would also like to thank the general chair of NAACL HLT 2009, Mari Ostendorf, the program committee chairs, Michael Collins, Lucy Vanderwende, Doug Oard, and Shri Narayanan, the publicity chairs Matthew Stone, Gokhan Tur, and Diana Inkpen, the publications chairs, Christy Doran and Eric Ringger, the local arrangements chairs, James Martin and Martha Palmer, and the ACL Business Manager, Priscilla Rasmussen, for all the support they have provided in the organization of this workshop. The faculty advisors and co-chairs of the NAACL HLT 2009 Student Research Workshop and Doctoral Consortium: Carolyn Penstein Rosī e Anoop Sarkar Svetlana Stoyanchev Ulrich Germann Chirag Shah

iii

Co-chairs: Ulrich Germann, University of Toronto, Canada Chirag Shah, University of North Carolina, USA Svetlana Stoyanchev, Stony Brook University, USA Faculty Advisors: Carolyn Penstein Rosī , Carnegie Mellon University, USA e Anoop Sarkar, Simon Fraser University, Canada Program Committee: Afra Alishahi Nguyen Bach Niranjan Balasubramanian Satanjeev Banerjee Regina Barzilay Shane Bergsma Alan Black Dan Bohus Sarah Borys Chris Callison-Burch Claire Cardie Marine Carpuat Colin Cherry Yejin Choi Paul Cook Steve DeNeefe Fernando Diaz Gregory Duck Kevin Duh Jason Eisner Afsaneh Fazly Jenny Finkel Victoria Fossum George Foster Yanfen Hao Sanjika Hewavitharana Derrick Higgins Silja Hildebrand Graeme Hirst Pierre Isabelle Howard Johnson Pallika Kanani Weimao Ke Diane Kelly Kevin Knight Philipp Koehn Greg Kondrak Roland Kuhn Shankar Kumar Giridhar Kumaran Philippe Langlais Brian Langner Gregor Leusch Adam Lopez Annie Louis Daniel Marcu Jonathan May David McClosky David Mimno Saif Mohammad Antonio Moreno Javed Mostafa Cristina Mota Smaranda Muresan Ani Nenkova Thuylinh Nguyen Oana Nicolov Christopher Parisien Joana Paulo Pardal Ted Pedersen Gerald Penn Hema Raghavan Ricardo Ribeiro Jason Riesa Ellen Riloff Mihai Rotaru Alex Rudnicky Frank Rudzicz Narges Sharif Razavian Michel Simard David Smith Yaxiao Song Richard Sproat Amanda Stent Veselin Stoyanov Joel Tetrault Dilek Tur Suzan Verberne Stephan Vogel Qin Iris Wang Nick Webb Ryen White Fan Yang Su-Youn Yoon Klaus Zechner Xiaodan Zhu

v

Table of Contents
Classifier Combination Techniques Applied to Coreference Resolution Smita Vemulapalli, Xiaoqiang Luo, John F. Pitrelli and Imed Zitouni . . . . . . . . . . . . . . . . . . . . . . . . . 1 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 . . . . 7 Exploring Topic Continuation Follow-up Questions using Machine Learning Manuel Kirschner and Raffaella Bernardi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 Sentence Realisation from Bag of Words with Dependency Constraints Karthik Gali and Sriram Venkatapathy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 Using Language Modeling to Select Useful Annotation Data Dmitriy Dligach and Martha Palmer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 Pronunciation Modeling in Spelling Correction for Writers of English as a Foreign Language Adriane Boyd . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 Building a Semantic Lexicon of English Nouns via Bootstrapping Ting Qian, Benjamin Van Durme and Lenhart Schubert . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 Multiple Word Alignment with Profile Hidden Markov Models Aditya Bhargava and Grzegorz Kondrak . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 Using Emotion to Gain Rapport in a Spoken Dialog System Jaime Acosta . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 Interactive Annotation Learning with Indirect Feature Voting Shilpa Arora and Eric Nyberg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 Loss-Sensitive Discriminative Training of Machine Transliteration Models Kedar Bellare, Koby Crammer and Dayne Freitag . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61 Syntactic Tree-based Relation Extraction Using a Generalization of Collins and Duffy Convolution Tree Kernel Mahdy Khayyamian, Seyed Abolghasem Mirroshandel and Hassan Abolhassani . . . . . . . . . . . . . 66 Towards Building a Competitive Opinion Summarization System: Challenges and Keys Elena Lloret, Alexandra Balahur, Manuel Palomar and Andrī s Montoyo . . . . . . . . . . . . . . . . . . . . 72 e Domain-Independent Shallow Sentence Ordering Thade Nahnsen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78 Towards Unsupervised Recognition of Dialogue Acts Nicole Novielli and Carlo Strapparava . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84

vii

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 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 90 Disambiguation of Preposition Sense Using Linguistically Motivated Features Stephen Tratz and Dirk Hovy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 96

viii

Conference Program
Monday, June 1, 2009 Morning Session 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 First Afternoon Session 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 Second Afternoon Session 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

11:15­11:45

11:50­12:20

2:35­3:05

4:35­5:05

5:10­5:40

ix

Monday, June 1, 2009 (continued) Poster Session (6:30­9:30) 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 Andrī s Montoyo e 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 All papers presented in the morning and afternoon sessions will also be shown as posters.

x