NAACL HLT 2009: Conference Program



Sunday, May 31, 2009 - Tutorials and Reception (Millennium Hotel)

7:00-6:00 Registration (Sunshire)
8:30-9:30 Coffee Service (Ballroom Atrium)
9:00-12:30 Morning Tutorials (Millennium Hotel)
Data-Intensive Text Processing with MapReduce
(Canyon Room)		 Extracting world/linguistic knowledge from Wikipedia
(Flagstaff Room)		 OpenFst: An Open-Source, Weighted FST Library
(Century Room)		 OntoNotes: The 90% Solution
(Millennium Room)
2:00-5:30 Afternoon Tutorials (Millennium Hotel)
Distributed Language Models
(Flagstaff Room)		 Search Algorithms in NLP: Theory and Practice with Dynamic Programming
(Canyon Room)		 VerbNet overview, extensions, mappings and apps
(Century Room)		 Writing Systems, Transliteration and Decipherment
(Millennium Room)
6:30-9:30 Welcome Reception (Millennium Hotel Gardens/Ballroom (rain))




Monday, June 1, 2009 - Main Conference (CU Campus)

7:00-6:00 Registration (UMC Lobby)
8:00 - 9:00 Coffee Service (West Ballroom)
8:45-9:00 Plenary - Welcome
9:00-10:10 Plenary - Invited Talk

East and Middle Ballroom

  • Understanding Visual Scenes:
    Antonio Torralba, Massachusetts Institute of Technology

    Abstract: Human visual scene understanding is remarkable: with only a brief glance at an image, an abundance of information is available - spatial structure, scene category and the identity of main objects in the scene. In traditional computer vision, scene and object recognition are two visual tasks generally studied separately. However, it is unclear whether it is possible to build robust systems for scene and object recognition, matching human performance, based only on local representations. Another key component of machine vision algorithms is the access to data that describe the content of images. As the field moves into integrated systems that try to recognize many object classes and learn about contextual relationships between objects, the lack of large annotated datasets hinders the fast development of robust solutions. In the early days, the first challenge a computer vision researcher would encounter would be the difficult task of digitizing a photograph. Even once a picture was in digital form, storing a large number of pictures (say six) consumed most of the available computational resources. In addition to the algorithmic advances required to solve object recognition, a key component to progress is access to data in order to train computational models for the different object classes. This situation has dramatically changed in the last decade, especially via the internet, which has given computer vision researchers access to billions of images and videos. In this talk I will describe recent work on visual scene understanding that try to build integrated models for scene and object recognition, emphasizing the power of large database of annotated images in computer vision.
10:10-10:40 Morning Break (Terrace/ West Ballroom)
10:40-12:20 Long Paper Session (25 min talks)

East Ballroom: Semantics

Session Chair: Philip Resnick
10:40-11:05 Subjectivity Recognition on Word Senses via Semi-supervised Mincuts
Fangzhong Su and Katja Markert
11:05-11:30 Integrating Knowledge for Subjectivity Sense Labeling
Yaw Gyamfi, Janyce Wiebe and Rada Mihalcea
11:30-11:55 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
11:55-12:20 A Fully Unsupervised Word Sense Disambiguation Method Using Dependency Knowledge
Ping Chen, Wei Ding, Chris Bowes and David Brown

CHEM 140: Multilingual processing / Morphology and Phonology

Session Chair: Sharon Goldwater
10:40-11:05 Learning Phoneme Mappings for Transliteration without Parallel Data
Sujith Ravi and Kevin Knight
11:05-11:30 A Corpus-Based Approach for the Prediction of Language Impairment in Monolingual English and Spanish-English Bilingual Children
Keyur Gabani, Melissa Sherman, Thamar Solorio and Yang Liu
11:30-11:55 A Discriminative Latent Variable Chinese Segmenter with Hybrid Word/Character Information
Xu Sun, Yaozhong Zhang, Takuya Matsuzaki, Yoshimasa Tsuruoka and Junichi Tsujii
11:55-12:20 Improved Reconstruction of Proto-Language Word Forms Alexandre Bouchard-Cote, Tom Griffiths and Dan Klein

UMC 235: Syntax and Parsing

Session Chair: Chris Manning
10:40-11:05 Shared Logistic Normal Distributions for Soft Parameter Tying in Unsupervised Grammar Induction
Shay Cohen and Noah A Smith
11:05-11:30 Adding More Languages Improves Unsupervised Multilingual Tagging: a Bayesian non-Parametric Approach
Benjamin Snyder, Tahira Naseem, Jacob Eisenstein and Regina Barzilay
11:30-11:55 Efficiently Parsable Extensions to Tree-Local Multicomponent TAG
Rebecca Nesson and Stuart Shieber
11:55-12:20 Improving Unsupervised Dependency Parsing with Richer Contexts and Smoothing
William P Headden III, Mark Johnson and David McClosky

UMC Aspen: Student Research Workshop Session I

10:40-11:10 Classifier Combination Techniques Applied to Coreference Resolution
Smita Vemulapalli, Xiaoqiang Luo, John F. Pitrelli and Imed Zitouni
11:15-11:45 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
11:50-12:20 Exploring Topic Continuation Follow-up Questions using Machine Learning
Manuel Kirschener and Raffaella Bernardi
12:20-2:00 Lunch Break

UMC 235: Student Lunch

The Student Research Workshop (SRW) at NAACL-HLT is pleased to announce a student lunch on Monday, June 1, 2009. This lunch is open to all students attending the conference (irrespective of their attendance at the SRW). The purpose of the lunch is to enable interactions among students attending the conference, and to discuss how the SRW and doctoral consortium should be run at NAACL and ACL. This will also serve as a forum in which students can feel free to voice their views about how these ACL conferences serve our student community in general.


The Student Research Workshop and Doctoral Consortium provide 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. This year, the SRW received 29 submissions from 11 countries.


The lunch is supported by a grant from the U.S. National Science Foundation (NSF).

2:00-3:30 Short Paper Sessions (15 min talks)

East Ballroom: Machine Translation

Session Chair: Bill Byrne
2:00-2:15 Cohesive Constraints in A Beam Search Phrase-based Decoder
Nguyen Bach, Stephan Vogel and Colin Cherry
2:15-2:30 Revisiting Optimal Decoding for IBM Machine Translation Model 4
James Clarke and Sebastian Riedel
2:30-2:45 Efficient Extraction of Oracle-best Translations from Hypergraphs
Zhifei Li and Sanjeev Khudanpur
2:45-3:00 Semantic Roles for SMT: A Hybrid Two-Pass Model
Dekai Wu and Pascale Fung
3:00-3:15 Comparison of Extended Lexicon Models in Search and Rescoring for SMT
Saša Hasan and Hermann Ney
3:15-3:30 Simplex Armijo Downhill Algorithm for Optimizing Statistical Machine Translation System Parameters
Bing Zhao and Shengyuan Chen

CHEM 140: Information Retrieval / Information Extraction / Sentiment

Session Chair: Janyce Wiebe
2:00-2:15 Translation Corpus Source and Size in Bilingual Retrieval
Paul McNamee, James Mayfield and Charles Nicholas
2:15-2:30 Large-scale Computation of Distributional Similarities for Queries
Enrique Alfonseca, Keith Hall and Silvana Hartmann
2:30-2:45 Text Categorization from Category Name via Lexical Reference
Libby Barak, Ido Dagan and Eyal Shnarch
2:45-3:00 Identifying Types of Claims in Online Customer Reviews Shilpa Arora, Mahesh Joshi and Carolyn Rose
3:00-3:15 Towards Automatic Image Region Annotation - Image Region Textual Coreference Resolution
Emilia Apostolova and Dina Demner-Fushman
3:15-3:30 TESLA: A Tool for Annotating Geospatial Language Corpora
Nate Blaylock, Bradley Swain and James Allen

UMC 235: Dialog / Speech / Semantics

Session Chair: Bhuvana Ramabhadran
2:00-2:15 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
2:15-2:30 Towards Natural Language Understanding of Partial Speech Recognition Results in Dialogue Systems
Kenji Sagae, Gwen Christian, David DeVault and David Traum
2:30-2:45 Spherical Discriminant Analysis in Semi-supervised Speaker Clustering
Hao Tang, Stephen Chu and Thomas Huang
2:45-3:00 Learning Bayesian Networks for Semantic Frame Composition in a Spoken Dialog System
Marie-Jean Meurs, Fabrice Lefèvre and Renato De Mori
3:00-3:15 Evaluation of a System for Noun Concepts Acquisition from Utterances about Images (SINCA) Using Daily Conversation Data
Yuzu Uchida and Kenji Araki
3:15-3:30 Web and Corpus Methods for Malay Count Classifier Prediction
Jeremy Nicholson and Timothy Baldwin

UMC Aspen: Student Research Workshop Session 2

2:00-2:30 Sentence Realisation from Bag of Words with Dependency Constraints
Karthik Gali and Sriram Venkatapathy
2:35-3:05 Using Language Modeling to Select Useful Annotation Data
Dmitriy Dligach and Martha Palmer
3:30-4:00 Afternoon Break (Terrace/West Ballroom)
4:00-5:40 Long Paper Sessions (25 min talks)

East Ballroom: Machine Translation

Session Chair: David Chiang
4:00-4:25 Context-Dependent Alignment Models for Statistical Machine Translation
Jamie Brunning, Adria de Gispert and William Byrne
4:25-4:50 Graph-based Learning for Statistical Machine Translation
Andrei Alexandrescu and Katrin Kirchhoff
4:50-5:15 Intersecting multilingual data for faster and better statistical translations
Yu Chen, Martin Kay and Andreas Eisele
5:15-5:40 No Presentation

CHEM 140: Semantics

Session Chair: Patrick Pantel
4:00-4:25 Without a `doubt'? Unsupervised discovery of downward-entailing operators Cristian Danescu-Niculescu-Mizil, Lillian Lee and Richard Ducott
4:25-4:50 The Role of Implicit Argumentation in Nominal SRL
Matthew Gerber, Joyce Chai and Adam Meyers
4:50-5:15 Jointly Identifying Predicates, Arguments and Senses using Markov Logic
Ivan Meza-Ruiz and Sebastian Riedel
5:15-5:40 Structured Generative Models for Unsupervised Named-Entity Clustering
Micha Elsner, Eugene Charniak and Mark Johnson

UMC 235: Information Retrieval

Session Chair: Sanjeev Khudanpur
4:00-4:25 Hierarchical Dirichlet Trees for Information Retrieval Gholamreza Haffari and Yee Whye Teh
4:25-4:50 Phrase-Based Query Degradation Modeling for Vocabulary-Independent Ranked Utterance Retrieval
J Scott Olsson and Douglas W Oard
4:50-5:15 Japanese Query Alteration Based on Lexical Semantic Similarity
Masato Hagiwara and Hisami Suzuki
5:15-5:40 Context-based Message Expansion for Disentanglement of Interleaved Text Conversations
Lidan Wang and Douglas Oard

UMC Aspen: Student Research Workshop Session 3

4:00-4:30 Pronunciation Modeling in Spelling Correction for Writers of English as a Foreign Language
Adriane Boyd
4:35-5:05 Building a Semantic Lexicon of English Nouns via Bootstrapping
Ting Qian, Benjamin Van Durme and Lenhart Schubert
5:10-5:40 Multiple Word Alignment with Profile Hidden Markov Models
Aditya Bhargava and Grzegorz Kondrak
6:30-9:30 Poster/demo session

Stadium Club at Folsom Field

Posters presenters can set up their posters in the Stadium Club anytime between 3:30 and 6:30.




Tuesday, June 2, 2009 - Main Conference (CU Campus)

7:30-6:00 Registration (UMC Lobby)
8:00 - 9:00 Coffee Service (West Ballroom)
9:00-10:10 Plenary - Paper Awards (30 min talks)

East and Middle Ballroom

Session Chair: Michael Collins
  • 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
10:10-10:40 Morning Break (Terrace/West Ballroom)
10:40-12:20 Long paper sessions (25 min talks)

East Ballroom: Machine Translation

Session Chair: Michael Collins
10:40-11:05 Efficient Parsing for Transducer Grammars
John DeNero, Mohit Bansal, Adam Pauls and Dan Klein
11:05-11:30 Preference Grammars Softening Syntactic Constraints to Improve Statistical Machine Translation
Ashish Venugopal, Andreas Zollmann, Noah Smith and Stephan Vogel
11:30-11:55 Using a Dependency Parser to Improve SMT for Subject-Object-Verb Languages
Peng Xu, Jaeho Kang, Michael Ringgaard and Franz Och
11:55-12:20 Learning Bilingual Linguistic Reordering Model for Statistical Machine Translation
Hanbin Chen, Jian-Cheng Wu and Jason S Chang

CHEM 140: Sentiment Analysis / Information Extraction

Session Chair: Ryan McDonald
10:40-11:05 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
11:05-11:30 Predicting Risk from Financial Reports with Regression
Shimon Kogan, Dimitry Levin, Bryan R Routledge, Jacob S Sagi and Noah A Smith
11:30-11:55 Domain Adaptation with Latent Semantic Association for Named Entity Recognition
Honglei GUO, Huijia ZHU, Zhili GUO, Xiaoxun ZHANG, Xian WU and Zhong SU
11:55-12:20 Semi-Automatic Entity Set Refinement
Vishnu Vyas and Patrick Pantel

UMC 235: Machine Learning / Morphology and Phonology

Session Chair: Kristina Toutanova
10:40-11:05 Unsupervised Constraint Driven Learning For Transliteration
Discovery Ming-Wei Chang, Dan Goldwasser, Dan Roth and Yuancheng Tu
11:05-11:30 On the Syllabification of Phonemes Susan Bartlett, Grzegorz Kondrak and Colin Cherry
11:30-11:55 Improving nonparameteric Bayesian inference experiments on unsupervised word segmentation with adaptor grammars
Mark Johnson and Sharon Goldwater
11:55-12:20 No presentation
12:20-2:00 Lunch Break
2:00-3:30 Short Paper Sessions (15 min talks)

East Ballroom: Machine Translation / Generation / Semantics

Session Chair: Anoop Sarkar
2:00-2:15 Statistical Post-Editing of a Rule-Based Machine Translation System
Antonio-L. Lagarda, Vicent Alabau, Francisco Casacuberta, Roberto Silva and Enrique Díaz-de-Liaño
2:15-2:30 On the Importance of Pivot Language Selection for Statistical Machine Translation
Michael Paul, Hirofumi Yamamoto, Eiichiro Sumita and Satoshi Nakamura
2:30-2:45 Tree Linearization in English: Improving Language Model Based Approaches
Katja Filippova and Michael Strube
2:45-3:00 Determining the position of adverbial phrases in English
Huayan Zhong and Amanda Stent
3:00-3:15 Estimating and Exploiting the Entropy of Sense Distributions
Peng Jin, Diana McCarthy, Rob Koeling and John Carroll
3:15-3:30 Semantic classification with WordNet kernels
Diarmuid Ó Séaghdha

CHEM 140: Machine Learning / Syntax

Session Chair: Hal Daumé III
2:00-2:15 Sentence Boundary Detection and the Problem with the U.S.
Dan Gillick
2:15-2:30 Quadratic Features and Deep Architectures for Chunking
Joseph Turian, James Bergstra and Yoshua Bengio
2:30-2:45 Active Zipfian Sampling for Statistical Parser Training
Onur Çobano˘glu
2:45-3:00 Combining Constituent Parsers
Victoria Fossum and Kevin Knight
3:00-3:15 Recognising the Predicate-argument Structure of Tagalog
Meladel Mistica and Timothy Baldwin
3:15-3:30 Reverse Revision and Linear Tree Combination for Dependency Parsing
Giuseppe Attardi and Felice Dell'Orletta

UMC 235: SPECIAL SESSION - Speech Indexing and Retrieval

Session Chair: Michiel Bacchiani and Eric Fosler-Lussier
2:00-2:15 Introduction
Michiel Bacchiani and Eric Fosler-Lussier
2:15-2:30 Anchored Speech Recognition for Question Answering
Sibel Yaman, Gokan Tur, Dimitra Vergyri, Dilek Hakkani-Tur, Mary Harper and Wen Wang
2:30-2:45 Score Distribution Based Term Specific Thresholding for Spoken Term Detection Dogan Can and Murat Saraclar
2:45-3:00 Automatic Chinese Abbreviation Generation Using Conditional Random Field
Dong Yang, Yi-Cheng Pan and Sadaoki Furui
3:00-3:15 Fast decoding for open vocabulary spoken term detection
Bhuvana Ramabhadran, Abhinav Sethy, Jonathan Mamou, Brian Kingsbury and Upendra Chaudhari
3:15-3:30 Tightly coupling Speech Recognition and Search
Taniya Mishra and Srinivas Bangalore
3:30-4:00 Afternoon Break (Terrace/West Ballroom)
4:00-5:15 Long Paper Sessions (25 min talks)

East Ballroom: Syntax and Parsing

Session Chair: David Weir
4:00-4:25 Joint Parsing and Named Entity Recognition
Jenny Rose Finkel and Christopher D Manning
4:25-4:50 Minimal-length linearizations for mildly context-sensitive dependency trees
Y Albert Park and Roger Levy
4:50-5:15 Positive Results for Parsing with a Bounded Stack using a Model-Based Right-Corner Transform
William Schuler

CHEM 140: Discourse and Summarization

Session Chair: Kevin Knight
4:00-4:25 Hierarchical Text Segmentation from Multi-Scale Lexical Cohesion
Jacob Eisenstein
4:25-4:50 Exploring Content Models for Multi-Document Summarization
Aria Haghighi
4:50-5:15 Latent Topic Models for Document Structure Induction
Harr Chen, SRK Branavan, Regina Barzilay and David R Karger

UMC 235: Spoken Language Systems

Session Chair: Prem Natarajan
4:00-4:25 Assessing and Improving the Performance of Speech Recognition for Incremental Systems
Timo Baumann, Michaela Atterer and David Schlangen
4:25-4:50 Geo-Centric Language Models for Local Business Voice Search
Amanda Stent, Ilija Zeljkovic, Diamantino Caseiro and Jay Wilpon
4:50-5:15 Improving the Arabic Pronunciation Dictionary for Phone and Word Recognition with Linguistically-Based Pronunciation Rules
Fadi Biadsy, Nizar Habash and Julia Hirschberg
6:00 Buses to NCAR
7:00-9:30 Banquet




Wednesday, June 3, 2009 - Main Conference (CU Campus)

7:30-6:00 Registration (UMC Lobby)
8:00 - 9:00 Coffee Service (West Ballroom)
9:00-10:10 Plenary - Invited Talk

East and Middle Ballroom

  • Ketchup, espresso, and chocolate chip cookies: Travels in the language of food
    Dan Jurafsky, Stanford University

    Abstract: What can the language of food tell us about human language more generally? Where do the words 'ketchup' and 'ceviche' come from, and what do they tell us about the global economic order of the last thousand years or so? Why does English borrow food words like 'espresso', 'pizza', and 'pasta' from Italian, but use native headwords for Italian artifacts like espresso machines, coffee grinders, frothers, and pizza ovens? And finally, what do turkeys have in common with Chinese broccoli, and what do chocolate chip cookies have in common with paper cups? I'll investigate these and other profound mysteries of eating and language.
10:10-10:40 Morning Break (Terrace/West Ballroom)
10:40-12:20 Long Paper Session (25 min talks)

East Ballroom: Machine Translation

Session Chair: Stephan Vogel
10:40-11:05 Using a maximum entropy model to build segmentation lattices for MT
Chris Dyer
11:05-11:30 Active Learning for Statistical Phrase-based Machine Translation
Gholamreza Haffari, Maxim Roy and Anoop Sarkar
11:30-11:55 Semi-Supervised Lexicon Mining from Parenthetical Expressions in Monolingual Web Pages
Xianchao Wu, Naoaki Okazaki and Junichi Tsujii
11:55-12:20 Hierarchical Phrase-Based Translation with Weighted Finite State Transducers
Gonzalo Iglesias, Adri de Gispert, Eduardo R Banga and William Byrne

CHEM 140: Speech Recognition and Language Modeling

Session Chair: Geoff Zweig
10:40-11:05 Improved pronunciation features for construct-driven assessment of non-native spontaneous speech
Lei Chen, Klaus Zechner and Xiaoming Xi
11:05-11:30 Performance Prediction for Exponential Language Models
Stanley Chen
11:30-11:55 Tied-Mixture Language Modeling in Continuous Space
Ruhi Sarikaya, Mohamed Afify and Brian Kingsbury
11:55-12:20 Shrinking Exponential Language Models
Stanley Chen

UMC 235: Sentiment Analysis

Session Chair: Lillian Lee
10:40-11:05 Predicting Response to Political Blog Posts with Topic Models
Tae Yano, William W Cohen and Noah A Smith
11:05-11:30 An Iterative Reinforcement Approach for Fine-Grained Opinion Mining
Weifu Du and Songbo Tan
11:30-11:55 For a few dollars less: Identifying review pages sans human labels
Luciano Barbosa, Ravi Kumar, Bo Pang and Andrew Tomkins
11:55-12:20 More than Words: Syntactic Packaging and Implicit Sentiment
Stephan Greene and Philip Resnik
12:20-1:40 Lunch Break
Pre-purchased Box lunches available in the East/Center Ballroom
12:40-1:40 Panel Discussion (East/Middle Ballroom)
Emerging Application Areas in Computational Linguistics
  • Chair:
    • Bill Dolan, Microsoft
  • Panelists:
    • Jill Burstein, Educational Testing Service
    • Joel Tetreault, Educational Testing Service
    • Patrick Pantel, Yahoo
    • Andy Hickl, Language Computer Corporation + Swingly

Abstract:

This panel will focus on emerging application areas in Computational Linguistics from an industry-oriented perspective. What kinds of commercial applications are likely to provide employment opportunities for graduating student several years from now? Are there particular technologies or applications that as a field we should be nurturing in a calculated effort to provide more funding and employment possibilities for future generations of students?


Please join us for a lunchtime conversation around these questions. Panelists representing a number of application areas will give a short talk sketching their thoughts on likely growth areas in CL, and will then be available for a QA session afterward.

1:40-2:30 NAACL Business Meeting (UMC 235)
2:30 - 3:45 Long Paper Sessions (25 min talks)

East Ballroom: Large-scale NLP

Session Chair: Ken Church
2:30-2:55 Streaming for large scale NLP Language Modeling
Amit Goyal, Hal Daumé and Suresh Venkatasubramanian
2:55-3:20 The Effect of Corpus Size on Case Frame Acquisition for Discourse Analysis
Ryohei Sasano, Daisuke Kawahara and Sadao Kurohashi
3:20-3:45 Semantic-based Estimation of Term Informativeness
Kirill Kireyev

CHEM 140: Syntax and Parsing

Session Chair: Jason Eisner
2:30-2:55 Optimal Reduction of Rule Length in Linear Context-Free Rewriting Systems
Carlos Gómez-Rodríguez, Marco Kuhlmann, Giorgio Satta and David Weir
2:55-3:20 Inducing Compact but Accurate Tree-Substitution Grammars
Trevor Cohn, Sharon Goldwater and Phil Blunsom
3:20-3:45 Hierarchical Search for Parsing
Adam Pauls and Dan Klein

UMC 235: Discourse and Summarization

Session Chair: Regina Barzilay
2:30-2:55 An effective Discourse Parser that uses Rich Linguistic Information
Rajen Subba and Barbara Di Eugenio
2:55-3:20 Graph-Cut-Based Anaphoricity Determination for Coreference Resolution
Vincent Ng
3:20-3:45 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
3:45 - 4:15 Afteroon Break (Terrace/West Ballroom)
4:15 - 5:30 Long Paper Sessions (25 min talks)

East Ballroom: Machine Learning

Session Chair: Noah Smith
4:15-4:40 Non-Parametric Bayesian Areal Linguistics
Hal Daumé III
4:40-5:05 Hierarchical Bayesian Domain Adaptation
Jenny Rose Finkel and Christopher D Manning
4:40-5:30 Online EM for Unsupervised Models
Percy Liang and Dan Klein

CHEM 140: Dialog Systems

Session Chair: David Traum
4:15-4:40 Unsupervised Approaches for Automatic Keyword Extraction Using Meeting Transcripts
Feifan Liu, Deana Pennell, Fei Liu and Yang Liu
4:40-5:05 A Finite-State Turn-Taking Model for Spoken Dialog Systems
Antoine Raux and Maxine Eskenazi
4:40-5:30 Extracting Social Meaning Identifying Interactional Style in Spoken Conversation
Dan Jurafsky, Rajesh Ranganath and Dan McFarland

UMC 235: Syntax and parsing

Session Chair: James Clark
4:15-4:40 Linear Complexity Context-Free Parsing Pipelines via Chart Constraints
Brian Roark and Kristy Hollingshead
4:40-5:05 Improved Syntactic Models for Parsing Speech with Repairs
Tim Miller
4:40-5:30 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




Thursday, June 4, 2009 - Workshops(CU Campus)

7:00-6:00 Registration (UMC Lobby)
8:30 - 9:15 Coffee Service (Middle Ballroom)
Workshops

Workshop

Room

9:00-6:00 CoNLL - Thirteenth Conference on Computational Natural Language Learning West Ballroom
9:00-5:30 BioNLP East Ballroom
9:00-6:00 SEW-2009 - Semantic Evaluations: Recent Achievements and Future Directions UMC Aspen
9:00-5:30 CLIAWS3 - Third International Workshop on Cross Lingual Information Access: Addressing the Information Need of Multilingual Societies UMC 384/386
9:20-5:30 Workshop on Integer Linear Programming for Natural Language Processing UMC 247
8:30-5:30 Computational Approaches to Linguistic Creativity UMC 415/417
9:00-5:40 Semi-supervised Learning for NLP UMC 235
10:30 - 11:00 Morning Break (Middle Ballroom)
12:30 - 2:00 Lunch Break
3:30 - 4:00 Afternoon Break (Middle Ballroom)




Friday, June 5, 2009 - Workshops (CU Campus)

7:30-5:30 Registration (UMC Lobby)
8:30 - 9:15 Coffee Service (Middle Ballroom)
Workshops

Workshop

Room

9:00-6:00 CoNLL - Thirteenth Conference on Computational Natural Language Learning West Ballroom
9:00-5:30 BioNLP East Ballroom
9:00-5:30 SETQA-NLP 2009 - Software Engineering, Testing, and Quality Assurance for Natural Language Processing UMC 384/386
9:00-5:00 Unsupervised and Minimally Supervised Learning of Lexical Semantics UMC Aspen
9:00-5:30 Active Learning for NLP UMC 247
9:00-5:30 Innovative Use of NLP for Building Educational Applications UMC 415/417
9:00-5:30 SSST - Third Workshop on Syntax and Structure in Statistical Translation UMC 235
10:30 - 11:00 Morning Break (Middle Ballroom)
12:30 - 2:00 Lunch Break
3:30 - 4:00 Afternoon Break (Middle Ballroom)