Program Schedule

Monday, June 10, 2013
8:45 Welcome to NAACL 2013!
9:00 Invited talk by Gina Kuperberg
Predicting Meaning: What the Brain tells us about the Architecture of Language Comprehension
10:10 Break
M1a: Machine Translation M1b: Information Extraction M1c: Cognitive and Psycholinguistics
10:40 Model With Minimal Translation Units, But Decode With Phrases
Durrani, Fraser, Schmid
Multi-faceted Event Recognition with Bootstrapped Dictionaries
Huang, Riloff
Extracting the Native Language Signal for Second Language Acquisition
Swanson, Charniak
11:05 Beyond Left-to-Right: Multiple Decomposition Structures for SMT
Zhang, Toutanova, Quirk, Gao
Named Entity Recognition with Bilingual Constraints
Che, Wang, Manning, Liu
An Analysis of Frequency- and Memory-Based Processing Costs
van Schijndel, Schuler
11:30 Improved Reordering for PBSMT using Sparse Features
Minimally Supervised Method for Multilingual Paraphrase Extraction
Yan, Hashimoto, Torisawa, Kawai, Kazama, Saeger
Cross-Lingual Semantic Similarity of Words as the Similarity of Their Semantic Word Responses
Vulić, Moens
11:55 Simultaneous Word-Morpheme Alignment for Statistical Machine Translation
Eyigoz, Gildea
Relation Extraction with Matrix Factorization and Universal Schemas
Riedel, Yao, McCallum
Combining multiple information types in Bayesian word segmentation
Doyle, Levy
12:20 Lunch
M2a: Parsing and Syntax M2b: Topic Modeling and Text Mining M2c: Spoken Language Processing
2:00 Training Parsers on Incompatible Treebanks
Representing Topics Using Images
Aletras, Stevenson
Text Alignment for Real-Time Crowd Captioning
Naim, Gildea, Lasecki, Bigham
2:25 Learning a Part-of-Speech Tagger from Two Hours of Annotation
Garrette, Baldridge
Summarizing Drug Experiences with Multi-Dimensional Topic Models
Paul, Dredze
Discriminative Joint Modeling of Lexical Variation and Acoustic Confusion for Automated Narrative Retelling Assessment
Lehr, Shafran, Prudhommeaux, Roark
2:50 Experiments with Spectral Learning of Latent-Variable PCFGs
Cohen, Stratos, Collins, Foster, Ungar
Towards Topic Labeling with Phrase Entailment and Aggregation
Mehdad, Carenini, T. NG, Rayhan Joty
Using Out-of-Domain Data for Lexical Addressee Detection in Human-Human-Computer Dialog
Lee, Stolcke, Shriberg
3:15 [TACL] Finding Optimal 1-Endpoint-Crossing Trees
Pitler, Kannan, Marcus
Topic Segmentation with a Structured Topic Model
Du, Buntine, Johnson
Segmentation Strategies for Streaming Speech Translation
Rangarajan Sridhar, Chen, Bangalore, Ljolje, Chengalvarayan
3:40 Break
4:10 Poster madness!
  1. Enforcing Subcategorization Constraints in a Parser Using Sub-parses Recombining (Mirroshandel, Nasr, Sagot)
  2. Large-Scale Discriminative Training for SMT (Flanigan, Dyer, Carbonell)
  3. Measuring Term Informativeness in Context (wu, Giles)
  4. Unsupervised Learning Summarization Templates (Saggion)
  5. Classification of South African languages using text and acoustic based methods: A case of six selected languages (Zulu)
  6. Improving Syntax-Augmented Machine Translation by Coarsening the Label Set (Hanneman, Lavie)
  7. Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression (Boudin, Morin)
  8. Development of a Persian Syntactic Dependency Treebank (Rasooli, Kouhestani, Moloodi)
  9. Improving reordering performance using higher order and structural features (Khapra, Ramanathan, Visweswariah)
  10. Massively Parallel Suffix Array Queries and On-Demand Phrase Extraction for Statistical Machine Translation Using GPUs (He, Lin, Lopez)
  11. [TACL] Branch and Bound Algorithm for Dependency Parsing with Non-local Features (Qian, Liu)
  12. Discriminative Training of 150 Million Translation Parameters and Its Application to Pruning (Setiawan, Zhou)
  13. Applying Pairwise Ranked Optimisation to Improve the Interpolation of Translation Models (Haddow)
  14. Dialectal Arabic to English Machine Translation: Pivoting through Modern Standard Arabic (Salloum, Habash)
  15. What to do about bad language on the internet (Eisenstein)
  16. Minibatch and Parallelization for Online Large-Margin Structured Learning (Zhao, Huang)
  17. Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters (Owoputi, O'Connor, Dyer, Gimpel, Schneider, Smith)
  18. Parser lexicalisation through self-learning (Rei, Briscoe)
  19. Mining User Relations from Online Discussions (Qiu, Yang, Jiang)
  20. Focused training sets to reduce noise in NER feature models (McKenzie)
  21. Learning to Relate Literal and Sentimental Descriptions of Visual Properties (Yatskar, Volkova, Celikyilmaz, Dolan, Zettlemoyer)
  22. Morphological Analysis and Disambiguation for Dialectal Arabic (Habash, Roth, Rambow, Eskander, Tomeh)
  23. Using a Supertagged Dependency Language Model to Select a Good Translation in System Combination (Ma, McKeown)
  24. Dudley North visits North London: Learning When to Transliterate to Arabic (Azab, Bouamor, Mohit, Oflazer)
  25. Better Twitter Summaries? (Judd, Kalita)
  26. Training MRF-Based Phrase Translation Models using Gradient Ascent (Gao, He)
  27. Automatic Morphological Enrichment of a Morphologically Underspecified Treebank (Alkuhlani, Habash, Roth)
  28. A Beam-Search Decoder for Normalization of Social Media Text with Application to Machine Translation (Wang, Ng)
  29. Parameter Estimation for LDA-Frames (Materna)
  30. Approximate PCFG Parsing Using Tensor Decomposition (Cohen, Satta, Collins)
  31. Negative Deceptive Opinion Spam (Ott, Cardie, Hancock)
  32. Improving speech synthesis quality by reducing pitch peaks in the source recordings (Violante, Rodriguez Zivic, Gravano)
  33. Robust Systems for Preposition Error Correction Using Wikipedia Revisions (Cahill, Madnani, Tetreault, Napolitano)
  34. Supervised Bilingual Lexicon Induction with Multiple Monolingual Signals (Irvine, Callison-Burch)
  35. Creating Reverse Bilingual Dictionaries (Lam, Kalita)
  36. Identification of Temporal Event Relationships in Biographical Accounts (Silcox, Tomai)
  37. Predicative Adjectives: An Unsupervised Criterion to Extract Subjective Adjectives (Wiegand, Ruppenhofer, Klakow)
  38. Modeling Syntactic and Semantic Structures in Hierarchical Phrase-based Translation (Li, Resnik, Daume III)
  39. Using Derivation Trees for Informative Treebank Inter-Annotator Agreement Evaluation (Kulick, Bies, Mott, Maamouri, Santorini, Kroch)
  40. A Comparison of Annotation Methodologies for Crowdsourcing Word Sense Labels (Jurgens)
  41. Compound Embedding Features for Semi-supervised Learning (Yu, Zhao, Dong, Tian, Yu)
  42. On Quality Ratings for Spoken Dialogue Systems -- Experts vs. Users (Ultes, Schmitt, Minker)
  43. Overcoming the Memory Bottleneck in Distributed Training of Latent Variable Models of Text (Yang, Yates, Downey)
  44. Processing Spontaneous Orthography (Eskander, Habash, Rambow, Tomeh)
  45. Purpose and Polarity of Citation: Towards NLP-based Bibliometrics (Abu-Jbara, Ezra, Radev)
  46. Estimating effect size across datasets (Søgaard)
  47. Systematic Comparison of Professional and Crowdsourced Reference Translations for Machine Translation (Zbib, Markiewicz, Matsoukas, Schwartz, Makhoul)
  48. Down-stream effects of tree-to-dependency conversions (Elming, Johannsen, Klerke, Lapponi, Martinez Alonso, Søgaard)
  49. From Language to Family and Back: Native Language and Language Family Identification from English Text (Stolerman, Caliskan, Greenstadt)
  50. Critical Reflections on Evaluation Practices in Coreference Resolution (Holen)
  51. A Rule-based Approach for Karmina Generation (Franky)
  52. A Machine Learning Approach to Automatic Term Extraction using a Rich Feature Set (Conrado, Pardo, Rezende)
  53. Ontology Label Translation (Arcan, Buitelaar)
  54. Entrainment in Spoken Dialogue Systems: Adopting, Predicting and Influencing User Behavior (Levitan)
  55. Helpfulness-Guided Review Summarization (Xiong)
  56. Statistical Machine Translation in Low Resource Settings (Irvine)
  57. Domain-Independent Captioning of Domain-Specific Images (Mason)
  58. Reversing Morphological Tokenization in English-to-Arabic SMT (Salameh, Cherry, Kondrak)
  59. Reducing Annotation Effort on Unbalanced Corpus based on Cost Matrix (Luo, Litman, Chan)
  60. User Goal Change Model for Spoken Dialog State Tracking (Ma)
  61. Large-Scale Paraphrasing for Natural Language Understanding (Ganitkevitch)
6:00 Break
6:30 Poster session & demonstrations
  1. DALE: A Word Sense Disambiguation System for Biomedical Documents Trained using Automatically Labeled Examples(Judita Preiss and Mark Stevenson)
  2. Topic Models and Metadata for Visualizing Text Corpora (Justin Snyder, Rebecca Knowles, Mark Dredze, Matthew Gormley and Travis Wolfe)
  3. TMTprime: A Recommender System for MT and TM Integration (Aswarth Abhilash Dara, Sandipan Dandapat, Declan Groves and Josef van Genabith)
  4. Anafora: A Web-based General Purpose Annotation Tool (Wei-Te Chen and William Styler)
  5. A Web Application for the Diagnostic Evaluation of Machine Translation over Specific Linguistic Phenomena(Antonio Toral, Sudip Kumar Naskar, Federico Gaspari and Declan Groves)
  6. KooSHO: Japanese Text Input Environment based on Aerial Hand Writing (Masato Hagiwara and Soh Masuko)
  7. UMLS::Similarity: Measuring the Relatedness and Similarity of Biomedical Concepts(Bridget McInnes, Ted Pedersen, Serguei Pakhomov, Ying Liu and Genevieve Melton-Meaux)
  8. KELVIN: a tool for automated knowledge base construction (Paul McNamee, James Mayfield, Tim Finin, Tim Oates, Dawn Lawrie, Tan Xu and Douglas Oard)
  9. Argviz: Interactive Visualization of Topic Dynamics in Multi-party Conversations (Viet An Nguyen, Yuening Hu, Jordan Boyd-Graber and Philip Resnik)
Tuesday, June 11, 2013
9:15 Best paper awards
9:25 Best Short Paper
The Life and Death of Discourse Entities: Identifying Singleton Mentions
Recasens, de Marneffe, Potts
9:45 Best Student Paper
Automatic Generation of English Respellings
Hauer, Kondrak
10:15 Break
T1a: Machine Translation and Multilinguality T1b: Sentiment Analysis and Topic Modeling T1c: Spoken Language Processing
10:45 A Simple, Fast, and Effective Reparameterization of IBM Model 2
Dyer, Chahuneau, Smith
A Multi-Dimensional Bayesian Approach to Lexical Style
Brooke, Hirst
A Cross-language Study on Automatic Speech Disfluency Detection
Wang, Stolcke, Yuan, Liberman
11:00 Phrase Training Based Adaptation for SMT
Mansour, Ney
Unsupervised Domain Tuning to Improve Word Sense Disambiguation
Preiss, Stevenson
Distributional semantic models for the evaluation of disordered language
Rouhizadeh, Prud'hommeaux, Roark, van Santen
11:15 Translation Acquisition Using Synonym Sets
Andrade, Tsuchida, Onishi, Ishikawa
Multi-Domain Learning for Multi-Attribute Data
Joshi, Dredze, Cohen, Rose
Atypical Prosodic Structure as an Indicator of Reading Level and Text Difficulty
Medero, Ostendorf
11:30 Supersense Tagging for Arabic: the MT-in-the-Middle Attack
Schneider, Mohit, Dyer, Oflazer, Smith
An opinion about opinions about opinions: subjectivity and the aggregate reader
Using Document Summarization Techniques for Speech Data Subset Selection
Wei, Liu, Kirchhoff, Bilmes
11:45 Zipfian corruptions for robust POS tagging
An Examination of Regret in Bullying Tweets
Xu, Burchfiel, Zhu, Bellmore
Semi-Supervised Discriminative Language Modeling with Out-of-Domain Text Data
Celebi, Saraclar
12:00 Lunch and Business Meeting (1:00-2:00)
T2a: Semantics T2b: Information Extraction T2c: Discourse and Dialog
2:00 Study of Human Cognition in Sense Annotation
Joshi, Kanojia, Bhattacharyya
Exploiting the Scope of Negations and Heterogeneous Features for Relation Extraction: A Case Study for Drug-Drug Interaction Extraction
Chowdhury, Lavelli
Differences in User Responses to a Wizard-of-Oz versus Automated System
Thomason, Litman
2:15 Improving Lexical Semantics for Sentential Semantics
Guo, Diab
Graph-Based Seed Set Expansion for Relation Extraction Using Random Walk Hitting Times
Lang, Henderson
Improving the Quality of Minority Class Identification in Dialog Act Tagging
Omuya, Prabhakaran, Rambow
2:30 Linguistic Regularities in Continuous Space Word Representations
Mikolov, Yih, Zweig
Distant Supervision for Relation Extraction with an Incomplete Knowledge Base
Min, Grishman, Wan, Wang, Gondek
Discourse Connectors for Latent Subjectivity in Sentiment Analysis
Trivedi, Eisenstein
2:45 TruthTeller: Annotating Predicate Truth
Lotan, Stern, Dagan
Measuring the Structural Importance through Rhetorical Structure Index
Kokhlikyan, Zhang, Waibel, Zhang
Coherence Modeling for the Automated Assessment of Spontaneous Spoken Responses
Wang, Evanini, Zechner
3:00 PPDB: The Paraphrase Database
Ganitkevitch, Van Durme, Callison-Burch
Separating Fact from Fear: Tracking Flu Infections on Twitter
Lamb, Paul, Dredze
Disfluency Detection Using Multi-step Stacked Learning
Qian, Liu
3:15 Break
T3a: Semantics T3b: Information Extraction T3c: Discourse
3:45 [TACL] Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions
Artzi, Zettlemoyer
Answer Extraction as Sequence Tagging with Tree Edit Distance
Yao, Van Durme, Callison-Burch, Clark
Same Referent, Different Words: Unsupervised Mining of Opaque Coreferent Mentions
Recasens, Can, Jurafsky
4:10 Using Semantic Unification to Generate Regular Expressions from Natural Language
Kushman, Barzilay
Open Information Extraction with Tree Kernels
Xu, Kim, Quinn, Goebel, Barbosa
Global Inference for Bridging Anaphora Resolution
Hou, Markert, Strube
4:35 Probabilistic Frame Induction
Cheung, Poon, Vanderwende
Finding What Matters in Questions
Luo, Raghavan, Castelli, Maskey, Florian
Classifying Temporal Relations with Rich Linguistic Knowledge
DSouza, Ng
5:00 A Quantum-Theoretic Approach to Distributional Semantics Blacoe, Kashefi, Lapata A Just-In-Time Keyword Extraction from Meeting Transcripts
Song, Go, Park, Park
Improved Information Structure Analysis of Scientific Documents Through Discourse and Lexical Constraints
Guo, Reichart, Korhonen
7:00 Banquet
Wednesday, June 12, 2013
9:00 Invited talk by Kathleen McKeown
Natural Language Applications from Fact to Fiction
10:10 Break
W1a: Machine Translation W1b: Semantics W1c: Social Media Processing
10:40 Adaptation of Reordering Models for SMT
Chen, Foster, Kuhn
Unsupervised Metaphor Identification Using Hierarchical Graph Factorization Clustering
Shutova, Sun
Broadly Improving User Classification via Clustering on Twitter
Bergsma, Dredze, Van Durme, Wilson, Yarowsky
11:05 Multi-Metric Optimization Using Ensemble Tuning
Sankaran, Sarkar, Duh
Three Knowledge-Free Methods for Automatic Lexical Chain Extraction
Remus, Biemann
To Link or Not to Link? A Study on End-to-End Tweet Entity Linking
Guo, Chang, Kiciman
11:30 Grouping Language Model Boundary Words to Speed K–Best Extraction from Hypergraphs
Heafield, Koehn, Lavie
Combining Heterogeneous Models for Measuring Relational Similarity
Zhila, Yih, Meek, Zweig, Mikolov
A Viewpoint Discovery Model
Qiu, Jiang
11:55 A Systematic Bayesian Treatment of the IBM Alignment Models
Gal, Blunsom
[TACL] Modeling Semantic Relations Expressed by Prepositions
Srikumar, Roth
Identifying Intention Posts in Discussion Forums
Chen, Liu, Hsu, Castellanos, Ghosh
12:20 Lunch
W2a: Parsing and Syntax W2b: Dialog W2c: Annotation and Language Resources
2:00 [TACL] Unsupervised Dependency Parsing with Acoustic Cues
Pate, Goldwater
Emergence of Gricean Maxims from Multi-Agent Decision Theory
Vogel, Bodoia, Potts, Jurafsky
Paving the Way to a Large-scale Pseudosense-annotated Dataset
Pilehvar, Navigli
2:25 Dependency-based empty category detection via phrase structure trees
Xue, Yang
Open Dialogue Management for Relational Databases
Hixon, Passonneau
Labeling the Languages of Words in Mixed-Language Documents using Weakly Supervised Methods
King, Abney
2:50 Target Language Adaptation of Discriminative Transfer Parsers
Täckström, McDonald, Nivre
A method for the approximation of incremental understanding of explicit utterance meaning using predictive models in finite domains
DeVault, Traum
Learning Whom to Trust with MACE
Hovy, Berg-Kirkpatrick, Vaswani, Hovy
3:15 Break
W3a: Semantics and Syntax W3b: Summarization and Generation W3c: Morphology and Phonology
3:45 Supervised All-Words Lexical Substitution using Delexicalized Features
Szarvas, Biemann, Gurevych
A Participant-based Approach for Event Summarization Using Twitter Streams
Shen, Liu, Weng, Li
Supervised Learning of Complete Morphological Paradigms
Durrett, DeNero
4:10 A Tensor-based Factorization Model of Semantic Compositionality
Van de Cruys, Poibeau, Korhonen
Towards Coherent Multi-Document Summarization
Christensen, Mausam, Soderland, Etzioni
Optimal Data Set Selection: An Application to Grapheme-to-Phoneme Conversion
Kim, Snyder
4:35 [TACL] An HDP Model for Inducing Combinatory Categorial Grammars
Bisk, Hockenmaier
Generating Expressions that Refer to Visible Objects
Mitchell, van Deemter, Reiter
Knowledge-Rich Morphological Priors for Bayesian Language Models
Chahuneau, Smith, Dyer
5:00 Conference adjourns!