EMNLP 2010: Conference on Empirical Methods in Natural Language Processing — October 9-11, 2010 — MIT, Massachusetts, USA.

Saturday, October 9, 2010

Plenary Session

Chair: Hang Li

• 8:50–9:00Opening remarks
• 9:00–10:00Invited Talk: Why do we call it decoding? Kevin Knight

Session 1A (Room 32-123): Syntactic Parsing and Machine Learning

Chair: Xavier Carreras

• 10:30–10:55On Dual Decomposition and Linear Programming Relaxations for Natural Language Processing Alexander M Rush, David Sontag, Michael Collins and Tommi Jaakkola
• 10:55–11:20Self-training with Products of Latent Variable Grammars Zhongqiang Huang, Mary Harper and Slav Petrov
• 11:20–11:45Utilizing Extra-sentential Context for Parsing Jackie Chi Kit Cheung and Gerald Penn
• 11:45–12:10Turbo Parsers: Dependency Parsing by Approximate Variational Inference Andre Martins, Noah Smith, Eric Xing, Pedro Aguiar and Mario Figueiredo

Session 1B (Room 32-141): Sentiment Analysis and Opinion Mining

Chair: Hanna Wallach

• 10:30–10:55Holistic Sentiment Analysis Across Languages: Multilingual Supervised Latent Dirichlet Allocation Jordan Boyd-Graber and Philip Resnik
• 10:55–11:20Jointly Modeling Aspects and Opinions with a MaxEnt-LDA Hybrid Xin Zhao, Jing Jiang, Hongfei Yan and Xiaoming Li
• 11:20–11:45Summarizing Contrastive Viewpoints in Opinionated Text Michael Paul, ChengXiang Zhai and Roxana Girju
• 11:45–12:10Automatically Producing Plot Unit Representations for Narrative Text Amit Goyal, Ellen Riloff and Hal Daume III

Session 1C (Room 32-155): Information Retrieval and Question Answering

Chair: Jing Jiang

• 10:30–10:55Handling Noisy Queries In Cross Language FAQ Retrieval Danish Contractor, Govind Kothari, Tanveer Faruquie, L. V. Subramaniam and Sumit Negi
• 10:55–11:20Learning the Relative Usefulness of Questions in Community QA Razvan Bunescu and Yunfeng Huang
• 11:20–11:45Positional Language Models for Clinical Information Retrieval Florian Boudin, Jian-Yun Nie and Martin Dawes
• 11:45–12:10Inducing Word Senses to Improve Web Search Result Clustering Roberto Navigli and Giuseppe Crisafulli

Session 2A (Room 32-123): Machine Translation I

Chair: Daniel Marcu

• 14:10–14:35Improving Translation via Targeted Paraphrasing Philip Resnik, Olivia Buzek, Chang Hu, Yakov Kronrod, Alex Quinn and Benjamin B. Bederson
• 14:35–15:00Soft Syntactic Constraints for Hierarchical Phrase-based Translation Using Latent Syntactic Distributions Zhongqiang Huang, Martin Cmejrek and Bowen Zhou
• 15:00–15:25A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages Minh-Thang Luong, Preslav Nakov and Min-Yen Ka
• 15:25–15:50"Poetic" Statistical Machine Translation: Rhyme and Meter Dmitriy Genzel, Jakob Uszkoreit and Franz Och

Session 2B (Room 32-141): Tagging, Chunking and Segmentation

Chair: Sharon Goldwater

• 14:10–14:35Efficient Graph-Based Semi-Supervised Learning of Structured Tagging Models Amarnag Subramanya, Slav Petrov and Fernando Pereira
• 14:35–15:00Better Punctuation Prediction with Dynamic Conditional Random Fields Wei Lu and Hwee Tou Ng
• 15:00–15:25Joint Training and Decoding Using Virtual Nodes for Cascaded Segmentation and Tagging Tasks Xian Qian, Qi Zhang, Yaqian Zhou, Xuanjing Huang and Lide Wu
• 15:25–15:50Crouching Dirichlet, Hidden Markov Model: Unsupervised POS Tagging with Context Local Tag Generation Taesun Moon, Katrin Erk and Jason Baldridge

Session 2C (Room 32-155): Text Mining

Chair: Hal Daumé III

• 14:10–14:35Improving Gender Classification of Blog Authors Arjun Mukherjee and Bing Liu
• 14:35–15:00Negative Training Data can be Harmful to Text Classification Xiao-Li Li, Bing Liu and See-Kiong Ng
• 15:00–15:25Modeling Organization in Student Essays Isaac Persing, Alan Davis and Vincent Ng
• 15:25–15:50Evaluating Models of Latent Document Semantics in the Presence of OCR Errors Daniel Walker, William B. Lund and Eric K. Ringger

Session 3A (Room 32-123): Machine Learning for NLP

Chair: Noah Smith

• 16:20–16:45Translingual Document Representations from Discriminative Projections John Platt, Kristina Toutanova and Wen-tau Yih
• 16:45–17:10Storing the Web in Memory: Space Efficient Language Models with Constant Time Retrieval David Guthrie and Mark Hepple
• 17:10–17:35Efficient Incremental Decoding for Tree-to-String Translation Liang Huang and Haitao Mi
• 17:35–18:00Modeling Perspective using Adaptor Grammars Eric Hardisty, Jordan Boyd-Graber and Philip Resnik

Session 3B (Room 32-141): Semantics

Chair: Mark Steedman

• 16:20–16:45Predicting The Semantic Compositionality of Prefix Verbs Shane Bergsma, Aditya Bhargava, Hua He and Grzegorz Kondrak
• 16:45–17:10Joint Inference for Bilingual Semantic Role Labeling Tao Zhuang and Chengqing Zong
• 17:10–17:35Automatic Discovery of Manner Relations and its Applications Eduardo Blanco and Dan Moldovan
• 17:35–18:00Tense Sense Disambiguation: a New Syntactic Polysemy Task Roi Reichart and Ari Rappoport

Session 3C (Room 32-155): Information Extraction

Chair: Ellen Riloff

• 16:20–16:45Improving Mention Detection Robustness to Noisy Input Radu Florian, John Pitrelli, Salim Roukos and Imed Zitouni
• 16:45–17:10Clustering-based Stratefied Seed Sampling for Semi-Supervised Semantic Relation Classification Longhua Qian and Guodong Zhou
• 17:10–17:35Unsupervised Discovery of Negative Categories in Lexicon Bootstrapping Tara McIntosh
• 17:35–18:00Automatic Keyphrase Extraction via Topic Decomposition Zhiyuan Liu, Wenyi Huang, Yabin Zheng and Maosong Sun

Sunday, October 10, 2010

Plenary Session

Chair: David Yarowsky

• 9:00–10:00Invited Talk: Unsupervised feature learning and Deep LearningAndrew Ng

Session 4A (Room 32-123): Discourse and Dialog

Chair: Rada Mihalcea

• 10:30–10:55Incorporating Content Structure into Text Analysis Applications Christina Sauper, Aria Haghighi and Regina Barzilay
• 10:55–11:20Exploiting Conversation Structure in Unsupervised Topic Segmentation for Emails Shafiq Joty, Giuseppe Carenini, Gabriel Murray and Raymond T. Ng
• 11:20–11:45A Semi-Supervised Approach to Improve Classification of Infrequent Discourse Relations using Feature Vector Extension Hugo Hernault, Danushka Bollegala and Mitsuru Ishizuka
• 11:45–12:10A Game-Theoretic Approach to Generating Spatial Descriptions Dave Golland, Percy Liang and Dan Klein

Session 4B (Room 32-141): Machine Translation II

Chair: Chris Quirk

• 10:30–10:55Facilitating Translation Using Source Language Paraphrase Lattices Jinhua Du, Jie Jiang and Andy Way
• 10:55–11:20Mining Name Translations from Entity Graph Mapping Gae-won You, Seung-won Hwang, Young-In Song, Long Jiang and Zaiqing Nie
• 11:20–11:45Non-isomorphic Forest Pair Translation Hui Zhang, Min Zhang, Haizhou Li and Eng Siong Chng
• 11:45–12:10Discriminative Instance Weighting for Domain Adaptation in Statistical Machine Translation George Foster, Cyril Goutte and Roland Kuhn

Session 4C (Room 32-155): NLP Applications

Chair: Manabu Okumura

• 10:30–10:55NLP on Spoken Documents without ASR Mark Dredze, Aren Jansen, Glen Coppersmith and Ken Church
• 10:55–11:20Fusing Eye Gaze with Speech Recognition Hypotheses to Resolve Exophoric References in Situated Dialogue Zahar Prasov and Joyce Y. Chai
• 11:20–11:45Multi-document Summarization Using Discriminative Learning and A* Search Ahmet Aker, Trevor Cohn and Robert Gaizauskas
• 11:45–12:10A Multi-pass Sieve for Coreference Resolution Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nate Chambers, Mihai Surdeanu, Dan Jurafsky and Christopher Manning

Session 5A (Room 32-123): Natural Language Generation

Chair: Dragomir Radev

• 14:10–14:35A Simple Domain-Independent Probabilistic Approach to Generation Gabor Angeli, Percy Liang and Dan Klein
• 14:35–15:00Title Generation with Quasi-Synchronous Grammar Kristian Woodsend, Yansong Feng and Mirella Lapata
• 15:00–15:25Automatic Analysis of Rhythmic Poetry with Applications to Generation and Translation Erica Greene, Tugba Bodrumlu and Kevin Knight

Session 5B (Room 32-141): Machine Translation III

Chair: David Chiang

• 14:10–14:35Discriminative Word Alignment with a Function Word Reordering Model Hendra Setiawan, Chris Dyer and Philip Resnik
• 14:35–15:00Hierarchical Phrase-based Translation Grammars Extracted from Alignment Posterior Probabilitie Adrià de Gispert, Juan Pino and William Byrne
• 15:00–15:25Maximum Entropy Based Phrase Reordering for Hierarchical Phrase-based Translation Zhongjun He, Yao MeNg and Hao Yu

Session 5C (Room 32-155): Language Resources

Chair: Benjamin Tsou

• 14:10–14:35Further Meta-Evaluation of Broad-Coverage Surface Realization Dominic Espinosa, Rajakrishnan Rajkumar, Michael White and Shoshana Berleant
• 14:35–15:00Two Decades of Unsupervised POS Induction: How Far Have We Come? Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman
• 15:00–15:25We're Not in Kansas Anymore: Detecting Domain Changes in Streams Mark Dredze, Tim Oates and Christine Piatko

Session 6A (Room 32-123): Poster Spotlights

Chair: Jason Eisner

• 15:55–17:30A Fast Fertility Hidden Markov Model for Word Alignment Using MCMC Shaojun Zhao and Daniel Gildea
•  Minimum Error Rate Training by Sampling the Translation Lattice Samidh Chatterjee and Nicola Cancedda
•  Statistical Machine Translation with a Factorized Grammar Libin Shen, Bing Zhang, Spyros Matsoukas, Jinxi Xu and Ralph Weischedel
•  Discriminative Sample Selection for Statistical Machine Translation Sankaranarayanan Ananthakrishnan, Rohit Prasad, David Stallard and Prem Natarajan
•  Effects of Empty Categories on Machine Translation Tagyoung Chung and Daniel Gildea
•  SCFG Decoding Without Binarization Mark Hopkins and Greg Langmead
•  Example-based Paraphrasing for Improved Phrase-Based Statistical Machine Translation Aurélien Max
•  Combining Unsupervised and Supervised Alignments for MT: An Empirical Study Jinxi Xu and Antti-Veikko Rosti
•  Top-Down Nearly-Context-Sensitive Parsing Eugene Charniak
•  Improved Fully Unsupervised Parsing with Zoomed Learning Roi Reichart and Ari Rappoport
•  Unsupervised Parse Selection for HPSG Rebecca Dridan and Timothy Baldwin
•  Uptraining for Accurate Deterministic Question Parsing Slav Petrov, Pi-Chuan Chang, Michael Ringgaard and Hiyan Alshawi
•  A Unified Framework for Scope Learning via Simplified Shallow Semantic Parsing Qiaoming Zhu, Junhui Li, Hongling Wang and Guodong Zhou
•  A New Approach to Lexical Disambiguation of Arabic Text Rushin Shah, Paramveer S. Dhillon, Mark Liberman, Dean Foster, Mohamed Maamouri and Lyle Ungar
•  What a Parser can Learn from a Semantic Role Labeler, and Vice Versa Stephen Boxwell, Dennis Mehay and Chris Brew
•  Word Sense Induction & Disambiguation Using Hierarchical Random Graphs Ioannis Klapaftis and Suresh Manandhar
•  Towards Conversation Entailment: An Empirical Investigation Chen Zhang and Joyce Chai
•  The Necessity of Combining Adaptation Methods Ming-Wei Chang, Michael Connor and Dan Roth
•  Training continuous space language models: some practical issues Hai Son Le, Alexandre Allauzen, Guillaume Wisniewski and François Yvon

Session 6B (Room 32-141): Poster Spotlights

Chair: Andrew McCallum

15:55–17:25Enhancing Domain Portability of Chinese Segmentation Model Using Chi-square Statistics and Bootstrapping Baobao Chang and Dongxu Han
•  Latent Descriptor Clustering for Unsupervised POS Induction Michael Lamar, Yariv Maron and Elie Bienenstock
•  A Probabilistic Morphological Analyzer for Syriac Peter McClanahan, George Busby, Robbie Haertel, Kristian Heal, Deryle Lonsdale, Kevin Seppi and Eric Ringger
•  Lessons Learned in Part-of-Speech Tagging of Conversational Speech Vladimir Eidelman, Zhongqiang Huang and Mary Harper
•  An Efficient Algorithm for Unsupervised Word Segmentation with Branching Entropy and MDL Valentin Zhikov, Hiroya Takamura and Manabu Okumura
•  A Fast Decoder for Joint Word Segmentation and POS-Tagging Using a Single Discriminative Model Yue Zhang and Stephen Clark
•  Simple Type-Level Unsupervised POS Tagging Yoong Keok Lee, Aria Haghighi and Regina Barzilay
•  Classifying Dialogue Acts in One-on-one Live Chats Su Nam Kim, Lawrence Cavedon and Timothy Baldwin
•  Resolving Event Noun Phrases to Their Verbal Mentions Bin Chen, Jian Su and Chew Lim Tan
•  A Tree Kernel-based Unified Framework for Chinese Zero Anaphora Resolution Fang Kong and Guodong Zhou
•  Automatic Comma Insertion for Japanese Text Generation Masaki Murata, Tomohiro Ohno and Shigeki Matsubara
•  Using Unknown Word Techniques To Learn Known Words Kostadin Cholakov and Gertjan van Noord
•  WikiWars: A New Corpus for Research on Temporal Expressions Pawel Mazur and Robert Dale
•  PEM: A Paraphrase Evaluation Metric Exploiting Parallel Texts Chang Liu, Daniel Dahlmeier and Hwee Tou Ng
•  Assessing Phrase-Based Translation Models with Oracle Decoding Guillaume Wisniewski, Alexandre Allauzen and François Yvon
•  Automatic Evaluation of Translation Quality for Distant Language Pairs Hideki Isozaki, Tsutomu Hirao, Kevin Duh, Katsuhito Sudoh and Hajime Tsukada
•  An Approach of Generating Personalized Views from Normalized Electronic Dictionaries : A practical Experiment on Arabic Language Aida Khemakhem, Bilel Gargouri and Abdelmajid Ben Hamadou
•  Generating Confusion Sets for Context-Sensitive Error Correction Alla Rozovskaya and Dan Roth

Session 6C (Room 32-155): Poster Spotlights

Chair: Philip Resnik

• 15:55–17:25Confidence in Structured-Prediction using Confidence-Weighted Models Avihai Mejer and Koby Crammer
•  Evaluating the Impact of Alternative Dependency Graph Encodings on Solving Event Extraction Tasks Ekaterina Buyko and Udo Hahn
•  Enhancing Mention Detection using Projection via Aligned Corpora Yassine Benajiba and Imed Zitouni19
•  Domain Adaptation of Rule-based Annotators for Named-Entity Recognition Tasks Laura Chiticariu, Rajasekar Krishnamurthy, Yunyao Li, Frederick Reiss and Shivakumar Vaithyanathan
•  Collective Cross-Document Relation Extraction Without Labelled Data Limin Yao, Sebastian Riedel and Andrew McCallum
•  Automatic Detection and Classification of Social Events Apoorv Agarwal and Owen Rambow
•  Extracting Opinion Targets in a Single- and Cross-Domain Setting with Conditional Random Fields Niklas Jakob and Iryna Gurevych
•  Multi-level Structured Models for Document-level Sentiment Classification Ainur Yessenalina, Yisong Yue and Claire Cardie
•  Cross Language Text Classification by Model Translation and Semi-Supervised Learning Lei Shi, Rada Mihalcea and Mingjun Tian
•  SRL-based Verb Selection for ESL Xiaohua Liu, Bo Han, Kuan Li, Stephan Hyeonjun Stiller and Ming Zhou
•  Context Comparison of Bursty Events in Web Search and Online Media Yunliang Jiang, Cindy Xide Lin and Qiaozhu Mei
•  Learning First-Order Horn Clauses from Web Text Stefan Schoenmackers, Jesse Davis, Oren Etzioni and Daniel Weld
•  Constraints based Taxonomic Relation Classification Quang Do and Dan Roth
•  A Semi-Supervised Method to Learn and Construct Taxonomies using the Web Zornitsa Kozareva and Eduard Hovy
•  Function-based Question Classification for General QA Fan Bu, Xingwei Zhu, Yu Hao and Xiaoyan Zhu
•  Learning Recurrent Event Queries for Web Search Ruiqiang Zhang, Yuki Konda, Anlei Dong, Pranam Kolari, Yi Chang and Zhaohui Zheng
•  Staying Informed: Supervised and Semi-Supervised Multi-View Topical Analysis of Ideological Perspective Amr Ahmed and Eric Xing
•  Word-based Dialect Identification with Georeferenced Rules Yves Scherrer and Owen Rambow

Poster Session and Reception (Walker memorial)

• 18:00–21:00All papers listed in sessions 6A, 6B and 6C will be presented in poster format