Beruflich Dokumente
Kultur Dokumente
Conference Handbook
IIT Bombay
proceeds. They were even less well equipped than we on the permanent committee to predict what they were getting into, but they have risen to the occasion in every way and you will find them to be immensely warm, helpful, and resourceful hosts. COLING's founding fathers wanted these conferences to be more than learned presentations. They wanted them to be opportunities to meet, and talk and delight in the company of others who share our fascination with language and the processes that make it work. Some call this the COLING spirit. There is nowhere that could nurture this spirit more effectively than here in India.
Martin Kay Christian Boitet Program Chairs, COLING 2012 December 2012
mountain ranges, about 90 km to the south-east of Mumbai. There will be cultural evening on the fourth day of the conference, featuring a solo performance on "tabla", the representative of Indian percussion instruments, and another solo on Sitar, an instrument that drew world's attention to Indian classical music tradition. Indian Institute of Technology Bombay is fittingly the host of COLING 2012. IITs have, over the years, emerged as the premier institutes of technology in India. The Computer Science and Engineering Department at IIT Bombay is one of the largest and oldest Departments of CSE in the country. Each and every member of the 40 strong NLP group at IIT Bombay is toiling hard to make COLING 2012 a resounding success. The Government and industries have been our generous sponsors. All their names and logos are to be found in printed and USB proceedings. We thank them wholeheartedly. Technology Development in Indian Languages (TDIL) project of Department of IT, Ministry of Communication and Information Technology, has been the motive force behind the growth of NLP in India. COLING happening in India is a result of this long history of active patronage. Logistics wise, the "large events"- inauguration, invited speeches, reception and the cultural program- are in the convocation hall of IIT Bombay. Oral presentations are all in the newly constructed Victor Menezes Convention
Center (VMCC) about 200 mtrs from the convocation hall. Poster presentations are in the convocation hall, except on the first day, when it is VMCC. A very competent team of volunteers will be available for any assistance. We hope COLING participants will have a memorable time in India. Pushpak Bhattacharyya Rajeev Sangal Organizing Chairs, COLING 2012 December 2012
TIME
VMCC AUDITORIUM
VMCC SH-22
VMCC SH-31
VMCC SH-32
VMCC SH-21
SH-01
SH-02
Registration (VMCC Lobby) WS-4 (1) Tea Break (VMCC Lobby) WS-4 (1) Lunch (VMCC Lobby) WS-4 (2) Tea Break (VMCC Lobby) WS-4 (2) Tutorial-6 (1) Tutorial-2 (2) Tutorial-4 (1) Tutorial-6 (1) Tutorial-2 (2) Tutorial-4 (1) Tutorial-5 (1) Tutorial-1 (1) Tutorial-3 (1) Tutorial-5 (1) Tutorial-1 (1) Tutorial-3 (1)
TIME
VMCC AUDITORIUM
VMCC SH-22
VMCC SH-31
VMCC SH-32
VMCC SH-21
SH-01
SH-02
Registration (VMCC Lobby) WS-11 Tea Break (VMCC Lobby) WS-11 Lunch (VMCC Lobby) WS-13 Tea Break (VMCC Lobby) WS-13 WS-8 (2) WS-9 (2) WS-14 (2) WS-6 (2) WS-8 (2) WS-9 (2) WS-14 (2) WS-6 (2) WS-8 WS-9 WS-14 WS-6 WS-8 WS-9 WS-14 WS-6
Page 2
TIME
VMCC AUDITORIUM
VMCC SH-22
VMCC SH-31
VMCC SH-32
VMCC SH-21
SH-01
SH-02
11:20-13:00
Machine Learning
Coreference resolution
Underresourced languages
Demo Session
Demo Session
13:00-14:30
Page 3
14:30-16:10
Summarization
Demo Session
Page 4
TIME
VMCC AUDITORIUM
VMCC SH-22
VMCC SH-31
VMCC SH-32
VMCC SH-21
SH-01
SH-02
10:00-11:20 11:20-13:00
Sentiment and text classification
Demo Session
Page 5
PROGRAM FOR COLING 2012 Content Extraction Underresourced & and Indian languages Disambiguation Deployment, integration & quality
14:30-16:10
Textual entailment
Summarization
Demo Session
19:30 onwards
Banquet at Renaissance
Excursion Day (Trip to Bhaja Caves) ICCL Business Meeting (Seminar Room, Jalvihar)
Page 6
TIME
VMCC AUDITORIUM
VMCC SH-22
VMCC SH-31
VMCC SH-32
VMCC SH-21
SH-01
SH-02
10:00-11:20 11:20-13:00
Empirical machine translation
Demo Session
Page 7
PROGRAM FOR COLING 2012 Translation and Information Retrieval Grammar and formalisms Annotation and Generation Resources and annotation
14:30-16:10
Summarization
Tea Break (VMCC Lobby) Underresourced languages Psychological and neurological modelling
Demo Session
Demo Session
Semantics
Tabla Solo by Shri. Prasad Padhye & Sitar by Pandit Nayan Ghosh
Page 8
TIME
VMCC AUDITORIUM
VMCC SH-22
VMCC SH-31
VMCC SH-32
VMCC SH-21
SH-01
SH-02
10:00-11:20 11:20-13:00
Empirical machine translation
Demo Session
Page 9
14:30-16:10
Information retrieval
Semantics
16:10-16:30 16:30-18:10
Tea Break (VMCC Lobby) Pragmatics, Disambiguation and Content Extraction Software Deployment and Translation
Demo Session
Demo Session
MT,IR,Sentiment
18:10-19:00
Page 10
TIME
VMCC AUDITORIUM
VMCC SH-22
VMCC SH-31
VMCC SH-32
VMCC SH-21
SH-01
SH-02
Registration (VMCC Lobby) WS-7 Tea Break (VMCC Lobby) WS-7 Lunch (VMCC Lobby) WS-5 (2) WS-7 (2) Tea Break (VMCC Lobby) WS-5 (2) WS-7 (2) WS-12 WS-1 (2) WS-10 (2) WS-2 (2) WS-12 WS-1 (2) WS-10 (2) WS-2 (2) WS-3 WS-1 WS-10 WS-2 WS-3 WS-1 WS-10 WS-2
Page 11
MAIN CONFERENCE
TIME SESSION CHAIR AND AUTHORS
Monday 10 December, 2012 Dec 10, Monday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 10, Monday 11:20-11:50 Translation and Parsing
Extraction of domain-specific bilingual lexicon from comparable corpora: compositional translation and ranking [#127]
Herv Blanchon Estelle Delpech, Batrice Daille, Emmanuel Morin and Claire Lemaire George Tambouratzis, Sokratis Sofianopoulos and Marina Vassiliou Djam Seddah, Benoit Sagot, Marie Candito, Virginie Mouilleron and Vanessa Combet Fei Xia Tim Van de Cruys, Laura Rimell, Thierry Poibeau and Anna Korhonen Youzheng Wu, Xugang Lu, Hitoshi Yamamoto, Shigeki Matsuda, Chiori Hori and Hideki Kashioka
Evaluating the translation accuracy of a novel languageindependent MT methodology [#434] The French Social Media Bank: a Treebank of Noisy User Generated Content [#954] Machine Learning Multi-way Tensor Factorization for Unsupervised Lexical Acquisition [#897] Factored Language Model based on Recurrent Neural Network [#612]
11:55-12:25
Page 12
12:30-13:00 Dec 10, Monday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 10, Monday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 10, Monday
Statistical Method of Building Dialect Language Models for ASR Systems [#1012] Coreference resolution Coreference Resolution with ILP-based Weighted Abduction [#989] Exploring Local and Global Semantic Information for Event Pronoun Resolution [#241] Easy-first Coreference Resolution [#997] Underresourced languages Incremental Learning of Affix Segmentation [#625] Tibetan Base Noun Phrase Identification Framework Based on Chinese-Tibetan Sentence Aligned Corpus [#167] Efficient Discrimination Between Closely Related Languages [#522] Software internationalization & localization
Naoki Hirayama, Shinsuke Mori and Hiroshi G. Okuno Ganesh Ramakrishnan Naoya Inoue, Ekaterina Ovchinnikova, Kentaro Inui and Jerry Hobbs Fang Kong and Guodong Zhou Veselin Stoyanov and Jason Eisner Aravind Joshi Wondwossen Mulugeta, Michael Gasser and Baye Yimam Ming Hua NUO, Hui Dan LIU, Wei Na ZHAO, Long Long MA, Jian WU and Zhi Ming DING Jrg Tiedemann and Nikola Ljube_i_ A Kumaran
Page 13
11:20-11:50 11:55-12:25 12:30-13:00 Dec 10, Monday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 10, Monday 14:30-15:00
An Evaluation of Statistical Post-editing Systems applied to RBMT and SMT Systems [#655] Inducing Crosslingual Distributed Representations of Words [#975] Attribute Extraction From Conjectural Queries [#1033] Expert or hybrid machine translation A Simplification-Translation-Restoration Framework for CrossDomain SMT Applications [#111] Alignment by Bilingual Generation and Monolingual Derivation [#631] Comparative quality estimation: Automatic sentence-level ranking of multiple Machine Translation outputs [#1038] Word Sense Disambiguation Expanding Microblog Context to Enhance Disambiguation to Wikipedia [#213]
Hanna Bchara, Raphal Rubino, Yifan He, Yanjun Ma and Josef van Genabith Alexandre Klementiev, Ivan Titov and Binod Bhattarai Marius Pasca Kartik Visweswariah Han-Bin Chen, Hen-Hsen Huang, Hsin-Hsi Chen and Ching-Ting Tan Toshiaki Nakazawa and Sadao Kurohashi Eleftherios Avramidis Malhar Kulkarni Taylor Cassidy, Heng Ji, Hongzhao Huang, Arkaitz Zubiaga, Lev-Arie Ratinov, Jing Zheng and Dan Roth
Page 14
15:05-15:35
Tailored Feature Extraction for Lexical Disambiguation of English Verbs Based on Corpus Pattern Analysis [#1110] Unsupervised Japanese-Chinese Opinion Word Translation Using Dependency Distance and Feature-Opinion Association Weight [#654] Discourse and Pragmatics Hunting for Entailing Pairs in the Penn Discourse Treebank. [#495] The Utility of Discourse Structure in Identifying Resolved Threads in Technical User Forums [#343] Implicitness of Discourse Relations [#598] Morphology & POS tagging Integrating Surface and Abstract Features for Robust CrossDomain Chinese Word Segmentation [#543] S-restricted monotone alignments: Algorithm, search space, and applications [#141]
Martin Holub, Vincent Kr_, Silvie Cinkov and Eckhard Bick Guo-Hau Lai, Ying-Mei Guo and Richard TzongHan Tsai Eva Hajiova Sara Tonelli and Elena Cabrio Li Wang, Su Nam Kim and Tim Baldwin Fatemeh Torabi Asr and Vera Demberg Josef van Genabith Xiaoqing Li, Kun Wang, Chengqing Zong and KehYih Su Steffen Eger
15:40-16:10 Dec 10, Monday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 10, Monday 14:30-15:00 15:05-15:35
Page 15
15:40-16:10 Dec 10, Monday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 10, Monday 16:30-17:00 17:05-17:35 17:40-18:10 Dec 10, Monday
Long-tail distributions and unsupevised learning of morphology [#494] Summarization A supervised aggregation framework for multi-document summarization [#362] Flexible Japanese Sentence Compression by Relaxing Unit Constraints [#594] Graph-based Multi-tweet Summarization Using Social Signals [#554] Sentiment and text classification Robust, Lexicalized Native Language Identification [#551] Native Language Identification Using Recurring N-grams Investigating Abstraction and Domain Dependence [#268] Automatic Detection of Point of View Differences in Wikipedia [#990] Word Sense Disambiguation
Qiuye Zhao and Mitch Marcus Asif Ekbal Yulong Pei, Wenpeng Yin, Qifeng Fan and Lian'en Huang Jun Harashima and Sadao Kurohashi Xiaohua Liu, Yitong Li, Furu Wei and Ming Zhou Karel Oliva Julian Brooke and Graeme Hirst Serhiy Bykh and Detmar Meurers Khalid Al Khatib and Hinrich Schutze Claire Gardent
Page 16
Improving Supervised Sense Disambiguation with Web-Scale Selectors [#833] Ant Colony Algorithm for the unsupervised Word Sense Disambiguation of texts: comparison and evaluation [#128] Joint Entity Disambiguation and Clustering [#976] Morphology Harnessing the CRF complexity with domain-specific constraints. The case of morphosyntactic tagging of a highly inflected language. [#938] Semi-supervised Representation Learning for Domain Adaptation [#1036] The Floating Arabic Dictionary: An Automatic Method for Updating a Lexical Database through the Detection and Lemmatization of Unknown Words [#131] Resources and annotation To Exhibit is not to Loiter: Measuring Verb Similarity using a Multilingual, Word Sense Disambiguated Wiktionary [#403]
Page 17
H. Andrew Schwartz, Fernando Gomez and Lyle H. Ungar Didier Schwab, Jrme Goulian, Andon Tchechmedjiev and Herv Blanchon Angela Fahrni and Michael Strube Amba Kulkarni
Jakub Waszczuk
17:05-17:35
Mohammed Attia, Younes Samih, Khaled Shaalan and Josef van Genabith Nicoletta Calzolari Christian M. Meyer and Iryna Gurevych
Problems in Evaluating Grammatical Error Detection Systems [#866] Annotation Tools and Knowledge Representation for a Text-ToScene System [#801] Named Entity recognition A machine learning approach for phenotype name recognition [#271] NEER: An Unsupervised Method for Named Entity Evolution Recognition [#232] Grammarless Parsing for Joint Inference [#1127]
Martin Chodorow, Markus Dickinson, Ross Israel and Joel Tetreault Bob Coyne, Alex Klapheke, Masoud Rouhizadeh, Richard Sproat and Daniel Bauer Amitabh Das Maryam Khordad, Robert E Mercer and Peter Rogan Nina Tahmasebi, Gerhard Gossen, Nattiya Kanhabua, Helge Holzmann and Thomas Risse Jason Naradowsky, Tim Vieira and David Smith
Page 18
Tuesday 11 December, 2012 Dec 11, Tuesday 11:20-11:50 11:55-12:25 Sentiment and text classification Readability Classification for German using lexical, syntactic, and morphological features [#725] Text Reuse Detection Using a Composition of Text Similarity Measures [#367] Native Tongues, Lost and Found: Resources and Empirical Evaluations in Native Language Identification [#1153] Speech and Summarization Language Modeling for Spoken Dialogue System based on Filtering using Predicate-Argument Structures [#861] Improving Text Normalization Using Character-blocks based Models and System Combination [#991] Topical Word Trigger Model for Keyphrase Extraction [#450] Nanda Kambhatla Julia Hancke, Sowmya Vajjala and Detmar Meurers Daniel Br, Torsten Zesch and Iryna Gurevych Joel Tetreault, Daniel Blanchard, Aoife Cahill, Beata Beigman-Klebanov and Martin Chodorow Advaith Siddharthan Koichiro Yoshino, Shinsuke Mori and Tatsuya Kawahara chen li and yang liu Zhiyuan Liu, Chen Liang and Maosong Sun
Page 19
Dec 11, Tuesday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 11, Tuesday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 11, Tuesday 11:20-11:50
Summarization
Sivaji Bandyopadhyay
Update Summarization Using a Multi-level Hierarchical Dirichlet Jiwei li, Sujian li, Xun Wang, Ye Tian and Baobao Process Model [#178] Chang Extractive Multi-Document Summarization with Integer Linear Programming and Support Vector Regression [#208] Bridging the Gap between Intrinsic and Perceived Relevance in Snippet Generation [#877] Underresourced languages and alignment JMaxAlign: A Maximum Entropy Parallel Sentence Alignment Tool [#814] Contribution of complex lexical information to solve syntactic ambiguity in Basque [#834] ISO-TimeML Event Extraction in Persian Text [#729] Psychological and neurological modelling Studying the effect of input size for Bayesian Word Segmentation on the Providence Corpus [#445]
Page 20
Dimitrios Galanis, Gerasimos Lampouras and Ion Androutsopoulos Jing He, Pablo Duboue and Jian-Yun Nie Ananthakrishnan Ramanathan Max Kaufmann Aitziber Atutxa, Eneko Agirre and Kepa Sarasola Ghassem-Sani and Seyed Abolghassem Mirroshandel William Schuler Benjamin Brschinger, Katherine Demuth and Mark Johnson
11:55-12:25 12:30-13:00 Dec 11, Tuesday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 11, Tuesday 14:30-15:00 15:05-15:35 15:40-16:10
Recognizing personal characteristics of readers using eyemovements and text features [#581] Implicit Discourse Relation Recognition by Selecting Typical Training Examples [#191] Content Extraction and Disambiguation Joint Modeling of Trigger Identification and Event Type Determination in Chinese Event Extraction [#151] Towards a Generic and Flexible Citation Classifier Based on a Faceted Classification Scheme [#216] Using Distributional Similarity for Lexical Expansion in Knowledge-based Word Sense Disambiguation [#368] Underresourced & Indian languages Improving Topic Classification for Highly Inflective Languages [#513] Differential Evolution based Feature Selection and Classifier Ensemble for Named Entity Recognition [#840] Sentiment Analysis in Twitter with Lightweight Discourse Analysis [#555]
Page 21
Pascual Martnez-Gmez, Tadayoshi Hara and Akiko Aizawa Xun Wang, Sujian Li, Jiwei Li, Wenjie Li Sobha Lalitha Devi Peifeng Li, Qiaoming Zhu, Hongjun Diao and Guodong Zhou Charles Jochim and Hinrich Schtze Tristan Miller, Chris Biemann, Torsten Zesch and Iryna Gurevych Jrg Tiedemann Jurgita Kapo_i_t_-Dzikien_, Frederik Vaassen, Walter Daelemans and Algis Krupavi_ius Utpal Kumar Sikdar, Asif Ekbal and Sriparna Saha Subhabrata Mukherjee and Pushpak Bhattacharyya
Dec 11, Tuesday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 11, Tuesday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 11, Tuesday 14:30-15:00
Deployment, integration & quality Detecting Word Ordering Errors in Chinese Sentences for Learning Chinese as a Foreign Language [#277] Generating ``A for Alpha'' When There Are Thousands of Characters [#572] A System For Multilingual Sentiment Learning On Big Data [#586] Textual entailment A Latent Discriminative Model for Compositional Entailment Relation Recognition Using Natural Logic [#1078] Paraphrasing for Style [#1000] User Behaviors Lend a Helping Hand: Learning Paraphrase Query Patterns from Search Log Sessions [#629] Summarization
Rajeev Sangal Chi-Hsin Yu and Hsin-Hsi Chen Hiroaki Kawasaki, Ryohei Sasano, Hiroya Takamura and Manabu Okumura Evan Anderson and Oles Zhulyn Deepak Khemani Yotaro Watanabe, Junta Mizuno, Eric Nichols, Naoaki Okazaki and Kentaro Inui Wei Xu, Alan Ritter, Bill Dolan, Ralph Grishman and Colin Cherry Shiqi Zhao, Haifeng Wang and Ting Liu Ramakanth Kavuluru
SentTopic-MultiRank: a novel ranking model for multi-document Wenpeng Yin, Yulong Pei, Fan Zhang and Lian'en summarization [#133] Huang
Page 22
15:05-15:35 15:40-16:10 Dec 11, Tuesday 16:30-17:00 17:05-17:35 17:40-18:10 Dec 11, Tuesday 16:30-17:00 17:05-17:35 17:40-18:10
Exploiting Category-Specific Information for Multi-Document Summarization [#518] RelationListwise for query-focused multi-document summarization [#157] Sentiment and text classification Statistical Mechanical Analysis of Semantic Orientations on Lexical Network [#561] Multi-View AdaBoost for Multilingual Subjectivity Analysis [#575] Finding Thoughtful Comments from Social Media [#503] Morphology and Corpora Modeling ESL Word Choice Similarities By Representing Word Intensions and Extensions [#1019] A Corpus-Based Study of Edit Categories in Featured and NonFeatured Wikipedia Articles [#473] A Diverse Dirichlet Process Ensemble for Unsupervised Induction of Syntactic Categories [#237]
Page 23
Jun-Ping Ng, Praveen Bysani, Ziheng Lin, Min-Yen Kan and Chew-Lim Tan Wenpeng Yin, Lifu Huang, Yulong Pei and Lian'en Huang Georges Fafiotte Takuma Goto, Yoshiyuki Kabashima and Hiroya Takamura Min Xiao and Yuhong Guo Swapna Gottipati and Jing Jiang Irawati Kulkarni Huichao Xue and Rebecca Hwa Johannes Daxenberger and Iryna Gurevych Roi Reichart, Gal Elidan and Ari Rappoport
Dec 11, Tuesday 16:30-17:00 17:05-17:35 17:40-18:10 Dec 11, Tuesday 16:30-17:00
Natural Language Generation Towards Automatic Topical Question Generation [#290] Adjective Deletion for Linguistic Steganography and Secret Sharing [#161] Error Mining with Suspicion Trees: Seeing the Forest for the Trees [#211] Question answering A Semi-Supervised Bayesian Network Model for Microblog Topic Classification [#775] Thread Specific Features Are Helpful For Identifying Subjectivity Orientation of Online Forum Threads [#806] Mining the Web for Large-Scale Conversational Content [#222] Named Entity recognition
Chris Biemann Yllias Chali and Sadid A. Hasan Ching-Yun Chang and Stephen Clark Shashi Narayan and Claire Gardent Kalika Bali Yan Chen, Zhoujun Li, Liqiang Nie, Xia Hu, Xiangyu Wang, Tat-Seng Chua and Xiaoming Zhang Prakhar Biyani, Sumit Bhatia, Cornelia Caragea and Prasenjit Mitra Wilson Wong, Lawrence Cavedon, John Thangarajah and Lin Padgham Gerard de Melo
Page 24
A Pipeline Arabic Named Entity Recognition Using a Hybrid Approach [#176] A Comparison and Improvement of Online Learning Algorithms for Sequence Labeling [#245] Initial explorations on using CRFs for Turkish Named Entity Recognition [#1044]
Mai Oudah and Khaled Shaalan Zhengyan He and Houfeng Wang Gkhan Akn _eker and Gl_en Eryi_it
Page 25
Thursday 13 December, 2012 Dec 13, Thursday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 13, Thursday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 13, Thursday Empirical machine translation Machine Translation by Modeling Predicate-Argument Structure Transformation [#657] Bilingual Lexicon Construction from Comparable Corpora via Dependency Mapping [#690] Unsupervised Discriminative Induction of Synchronous Grammar for Machine Translation [#874] Parsing Improvements to Training an RNN Parser [#574] A Dynamic Oracle for Arc-Eager Dependency Parsing [#842] Exploiting Lexical Dependencies from Large-Scale Data for Better Shift-Reduce Constituency Parsing [#742] Question answering Holger Schwenk Feifei Zhai, Jiajun Zhang, Yu Zhou and Chengqing Zong Longhua Qian, Hongling Wang, Guodong Zhou and Qiaoming Zhu Xinyan Xiao, Deyi Xiong, Yang Liu, Qun Liu and Shouxun Lin Mark Johnson Richard Billingsley and James Curran Yoav Goldberg and Joakim Nivre Muhua Zhu, Jingbo Zhu and Huizhen Wang L V Subramaniam
Page 26
11:20-11:50 11:55-12:25 12:30-13:00 Dec 13, Thursday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 13, Thursday 11:20-11:50
Answering Yes/No Questions via Question Inversion [#400] Multi-dimensional feature merger for Question Answering [#946] The Use of Dependency Relation Graph to Enhance the Term Weighting in Question Retrieval [#649] Ontologies and terminology Method mention extraction from scientific research papers [#1155] Bayesian Text Segmentation for Index Term Identification and Keyphrase Extraction [#505] Constructing Reference Semantic Predictions from Biomedical Knowledge Sources [#156] Discourse and Pragmatics Whos (Really) the Boss? Perception of Situational Power in Written Interactions [#1149]
Hiroshi Kanayama, Yusuke Miyao and John Prager Apoorv Agarwal, J William Murdock, Jennifer Chu-Carroll, Adam Lally and Aditya Kalyanpur Weinan Zhang, Zhaoyan Ming, Yu Zhang, Liqiang Nie, Ting Liu and Tat-Seng Chua Michael Glass Hospice Houngbo and Robert Mercer David Newman, Nagendra Koilada, Jey Han Lau and Timothy Baldwin Demeke Ayele, Jean-Pierre Chevallet, Million Meshesha and Getnet Kassie Peter Scharf Vinodkumar Prabhakaran, Owen Rambow and Mona Diab
Page 27
11:55-12:25
Modeling Leadership and Influence in Multi-party Online Discourse [#510] Constrained decoding for text-level discourse parsing [#671] Translation and Information Retrieval Inverse Document Density: A Smooth Measure for LocationDependent Term Irregularities [#259] N-gram Fragment Sequence Based Unsupervised DomainSpecific Document Readability [#623] Approximate Sentence Retrieval for Scalable and Efficient Example-based Machine Translation [#795] Grammar and formalisms Semantics-Based Machine Translation with Hyperedge Replacement Grammars [#1098] From Finite-State to Inversion Transductions: Toward Unsupervised Bilingual Grammar Induction [#1112]
12:30-13:00 Dec 13, Thursday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 13, Thursday 14:30-15:00 15:05-15:35
Tomek Strzalkowski, Samira Shaikh, Ting Liu, George Aaron Broadwell, Jenny Stromer-Galley, Sarah Taylor, Umit Boz, Veena Ravishankar and Xiaoai Ren Philippe Muller, Stergos Afantenos, Pascal Denis and Nicholas Asher Rohit Prasad Dennis Thom, Harald Bosch and Thomas Ertl Shoaib Jameel, Xiaojun Qian and Wai Lam Johannes Leveling, Debasis Ganguly, Sandipan Dandapat and Gareth Jones Gabor Proszeky Bevan Jones, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann and Kevin Knight Markus Saers, Karteek Addanki and Dekai Wu
Page 28
15:40-16:10 Dec 13, Thursday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 13, Thursday
A Comprehensive Analysis of Constituent Coordination for Grammar Engineering [#992] Summarization On the Effectiveness of Using Sentence Compression Models for Query-Focused Multi-Document Summarization [#426] Twitter Topic Summarization by Ranking Tweets Using Social Influence and Content Quality [#478] Context-Enhanced Personalized Social Summarization [#404] Annotation and Generation Natural Language Generation for Nature Conservation: Automating Feedback to help Volunteers identify Bumblebee Species [#331]
Agnieszka Patejuk and Adam Przepirkowski David Rouquet Yllias Chali and Sadid A. Hasan Yajuan Duan, Zhumin Chen, Furu Wei, Ming Zhou and Heung-Yeung Shum Po Hu, Donghong Ji, Chong Teng and Yujing Guo Paul Kiparsky Steven Blake, Advaith Siddharthan, Hien Nguyen, Nirwan Sharma, Anne-Marie Robinson, Elaine O'Mahony, Ben Darvill, Chris Mellish and Rene van der Wal
14:30-15:00
15:05-15:35 15:40-16:10
Modeling the Complexity of Manual Annotation Tasks: a Grid of Karen Fort, Adeline Nazarenko and Sophie Rosset Analysis [#251] The Secret's in the Word Order: Text-to-Text Generation for Linguistic Steganography [#149] Ching-Yun Chang and Stephen Clark
Page 29
Resources and annotation Creating an Extended Named Entity Dictionary from Wikipedia [#541] Learnability-based Syntactic Annotation Design [#198]
Sriram Venkatapathy Ryuichiro Higashinaka, Kugatsu Sadamitsu, Kuniko Saito, Toshiro Makino and Yoshihiro Matsuo Roy Schwartz, Omri Abend and Ari Rappoport Eduard Bejcek, Jarmila Panevova, Jan Popelka, Pavel Stranak, Magda Sevcikova, Jan Stepanek and Zdenek Zabokrtsky Sadao Kurohashi Preslav Nakov, Francisco Guzman and Stephan Vogel Minwei Feng, Weiwei Sun and Hermann Ney Jan A. Botha, Chris Dyer and Phil Blunsom Owen Rambow
15:05-15:35
15:40-16:10 Dec 13, Thursday 16:30-17:00 17:05-17:35 17:40-18:10 Dec 13, Thursday
Empirical machine translation Optimizing for Sentence-Level BLEU+1 Yields Short Translations [#617] Semantic Cohesion Model for Phrase-based SMT [#884] Bayesian Language Modelling of German Compounds [#1074] Parsing
Page 30
16:30-17:00 17:05-17:35 17:40-18:10 Dec 13, Thursday 16:30-17:00 17:05-17:35 17:40-18:10 Dec 13, Thursday 16:30-17:00 17:05-17:35
Stacking Heterogeneous Joint Models of Chinese POS Tagging and Dependency Parsing [#717] Improving Combinatory Categorial Grammar Parse Reranking with Dependency Grammar Features [#424] Stacking of Dependency and Phrase Structure Parsers [#896] Semantics Unsupervised Discovery of Relations and Discriminative Extraction Patterns [#809] Improved Temporal Relation Classification using Dependency Parses and Selective Crowdsourced Annotations [#770] Grounded Language Acquisition: A Minimal Commitment Approach [#761] Underresourced languages Employing Morphological Structures and Sememes for Chinese Event Extraction [#310] A Collaborative Platform for Sanskrit Processing [#764]
Meishan Zhang, Wanxiang Che, Ting Liu and Zhenghua Li Sunghwan Mac Kim, Dominick Ng, Mark Johnson and James Curran Richard Farkas and Bernd Bohnet Igor Boguslavsky Alan Akbik, Larysa Visengeriyeva, Priska Herger, Holmer Hemsen and Alexander Lser Jun-Ping Ng and Min-Yen Kan Sushobhan Nayak and Amitabha Mukerjee Vincent Berment Peifeng Li and Guodong Zhou Pawan Goyal, Grard Huet, Amba Kulkarni, Peter Scharf and Ralph Bunker
Page 31
Deriving a Lexicon for a Precision Grammar from Language Documentation Resources: A Case Study of Chintang [#371] Psychological and neurological modelling
Mining words in the minds of second language learners: learner- Yo Ehara, Issei Sato, Hidekazu Oiwa and Hiroshi specific word difficulty [#1002] Nakagawa Automatic Detection of Psychological Distress Indicators and Severity Assessment from Online Forum Posts [#1093] A Computational Cognitive Model for Semantic Sub-network Extraction from Natural Language Queries [#316] Shirin Saleem, Shiv Vitaladevuni, Maciej Pacula and Rohit Prasad Suman Deb Roy and Wenjun Zeng
Page 32
Friday 14 December, 2012 Dec 14, Friday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 14, Friday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 14, Friday Empirical machine translation Translation Quality-Based Supplementary Data Selection by Incremental Update of Translation Models [#520] A Comparison of Syntactic Reordering Methods for EnglishGerman Machine Translation} [#560] Tree-based Translation without Using Parse Trees [#489] Parsing Easy-First, Chinese, POS Tagging and Dependency Parsing [#616] Mining Rules for Rewriting States in a Transition-based Dependency Parser for English [#309] Chengqing Zong Pratyush Banerjee, Sudip Naskar, Johann Roturier, Andy Way and Josef van Genabith Jiri Navratil, Karthik Visweswariah and Ananthakrishnan Ramanathan Feifei Zhai, Jiajun Zhang, Yu Zhou and Chengqing Zong Chu-Ren Huang Ji Ma, Tong Xiao, JingBo Zhu and Feiliang Ren Akihiro Inokuchi and Ayumu Yamaoka
A Separately Passive-Aggressive Training Algorithm for Joint POS Zhenghua Li, Min Zhang, Wanxiang Che and Ting Tagging and Dependency Parsing [#446] Liu Semantics Sara Tonelli
Page 33
11:20-11:50 11:55-12:25 12:30-13:00 Dec 14, Friday 11:20-11:50 11:55-12:25 12:30-13:00 Dec 14, Friday 11:20-11:50 11:55-12:25
Learning Effective and Interpretable Semantic Models using Non Brian Murphy, Partha Talukdar and Tom Mitchell Negative Sparse Coding [#1088] Learning Compositional Semantics for Open Domain Semantic Parsing [#882] Deriving Paraphrases for Highly-Inflected Languages from Comparable Documents [#645] Ontologies and terminology Combining Wordnet and morphosyntactic information in terminology clustering [#687] Experiments with Term Translation [#474] Structured Term Recognition in Medical Text [#923] Indian language technology Semantic Processing of Compounds in Indian Languages [#1034] Phong Le and Willem Zuidema Kfir Bar and Nachum Dershowitz Tim Baldwin Agnieszka Mykowiecka and Malgorzata Marciniak Mihael Arcan, Christian Federmann and Paul Buitelaar Michael Glass and Alfio Gliozzo Dipti Sharma Amba Kulkarni, Soma Paul, Malhar Kulkarni, Anil Kumar and Nitesh Surtani
Noun Group and Verb Group Identification for Hindi POS Tagging Smriti Singh, Om P. Damani and Vaijayanthi M. [#835] Sarma
Page 34
12:30-13:00
YouCat: Weakly Supervised Youtube Video Categorization System from Meta Data & User Comments using WordNet & Wikipedia [#557] Information retrieval Unsupervised and semi-supervised morphological analysis for Information Retrieval in the biomedical domain [#979] Combining Statistical Translation Techniques for Cross-Language Information Retrieval [#441] Measuring the similarity between TV programs using semantic relations [#467] Machine Translation and Grammar Simple and Effective Parameter Tuning for Domain Adaptation of Statistical Machine Translation [#641] Flexible Structural Analysis of Near-Meet-Semilattices for Typed Unification-based Grammar Design [#1116] Identifying Urdu Complex Predication via Bigram Extraction [#758]
Subhabrata Mukherjee and Pushpak Bhattacharyya Monojit Choudhury Vincent Claveau Ferhan Ture, Jimmy Lin and Douglas W. Oard Ichiro Yamada, Masaru Miyazaki, Hideki Sumiyoshi, Atsushi Matsui, Hironori Furumiya and Hideki Tanaka Ulrich Schaefer Pavel Pecina, Antonio Toral and Josef van Genabith Rouzbeh Farahmand and Gerald Penn Tafseer Ahmed, Tina Bgel, Miriam Butt, Annette Hautli and Sebastian Sulger
15:40-16:10
Page 35
Dec 14, Friday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 14, Friday 14:30-15:00 15:05-15:35 15:40-16:10 Dec 14, Friday 14:30-15:00
Semantics Accurate Unbounded Dependency Recovery using Generalized Categorial Grammars [#1046] Semi-Supervised Semantic Role Labeling: Approaching from an Unsupervised Perspective [#786] Walk-based Computation of Contextual Word Similarity [#1076] Natural Language Generation Towards efficient HPSG generation for German, a nonconfigurational language [#936] Quantifying Semantics Using Complex Network Analysis [#146] Structure-Driven Lexicalist Generation [#506] Ontologies and terminology Revising the Compositional Method for Terminology Acquisition from Comparable Corpora [#477]
Page 36
Massimo Poesio Luan Nguyen, Marten Van Schijndel and William Schuler Ivan Titov and Alexandre Klementiev Kazuo Hara, Ikumi Suzuki, Masashi Shimbo and Yuji Matsumoto Om Damani Berthold Crysmann and Woodley Packard Chris Biemann, Stefanie Roos and Karsten Weihe Shashi Narayan and Claire Gardent Philippe Blache Emmanuel Morin and Batrice Daille
Comparing taxonomies for organising collections of documents Samuel Fernando, Mark Hall, Eneko Agirre, Aitor [#255] Soroa, Paul Clough and Mark Stevenson IE & text mining Veselin Stoyanov Hongzhao Huang, Arkaitz Zubiaga, Heng Ji, Hongbo Deng, Dong Wang, Hieu Khac Le, Tarek Abdelzaher, Jiawei Han, Alice Leung, John Hancock and Clare Voss Wei Zhang, Jian Su and Chew-Lim Tan Hassan Sajjad, Patrick Pantel and Michael Gamon Dekai Wu Chen Chen and Vincent Ng Yiou Wang, Junichi Kazama, Takuya Kawada and Kentaro Torisawa
16:30-17:00
Tweet Ranking based on Heterogeneous Networks [#285] A Lazy Learning Model for Entity Linking Using Query-Specific Information [#583] Refinement of Underspecified Queries via Natural Language Question Generation from Unstructured Text [#276] Extraction from Text Joint Modeling for Chinese Event Extraction with Rich Linguistic Features [#1157] Chinese Evaluative Information Analysis [#1057]
Page 37
Understanding the Performance of Statistical MT Systems: A Linear Regression Framework [#525] Pragmatics, Disambiguation and Content Extraction A hybrid approach to finding phenotype candidates in genetic texts [#618] Identification of Social Acts in Dialogue [#514] Geolocation Prediction in Social Media Data by Finding Location Indicative Words [#566] Software Deployment and Translation SpeedRead: A Fast Named Entity Recognition Pipeline [#132]
Francisco Guzman and Stephan Vogel Tim Van de Cruys Nigel Collier, Mai-Vu Tran, Hoang-Quynh Le, Anika Oellrich, Ai Kawazoe, Martin Hall-May and Dietrich Rebholz-Schuhmann David Bracewell, Marc Tomlinson and Hui Wang Bo Han, Paul Cook and Timothy Baldwin Herv Blanchon Rami Al-Rfou' and Steven Skiena
16:30-17:00
17:05-17:35
Extraction of domain-specific bilingual lexicon from comparable Estelle Delpech, Batrice Daille, Emmanuel Morin corpora: compositional translation and ranking [#127] and Claire Lemaire Code Switching Language Model with Inversion Constraints for Mixed Language Speech Recognition [#1085] Ying Li and Pascale Fung
17:40-18:10
Page 38
MT, IR, Sentiment Sub-corpora Sampling with an Application to Bilingual Lexicon Extraction [#493] Cross-Lingual Topical Relevance Models [#158] Extraction of Russian Sentiment Lexicon for Product MetaDomain [#363]
Vincent Claveau Ivan Vuli_ and Marie-Francine Moens Debasis Ganguly, Johannes Leveling and Gareth Jones Ilia Chetviorkin and Natalia Loukachevitch
Page 39
TUTORIALS
ID TITLE SPEAKERS
T1 T2 T3 T4 T5 T6
Temporal Information Extraction and Shallow Temporal Reasoning Exploiting Web Data Sources for Advanced NLP Multimodal Corpora The Hindi/Urdu Treebank: New Frontiers in Hindi and Urdu Natural Language Processing Open-domain Conversations with Humanoid Robots Revisiting Dimensionality Reduction Techniques for NLP
Prof. Dan Roth, Prof. Heng Ji, Taylor Cassidy, Quang Do Dr. Gerard de Melo Prof. Patrizia Paggio, Prof. Dirk Heylen, Prof. Costanza Navarretta Prof. Owen Rambow, Prof. Dipti Misra Sharma, Ashwini Vaidya Prof. Kristiina Jokinen, Prof Graham Wilcock Jagadeesh Jagarlamudi, Raghavendra Udupa
Page 40
WORKSHOPS
ID TITLE ORGANIZERS
Advances in discourse analysis and its computational aspects Second Workshop on Advances in Text Input Methods (WTIM 2) Eye-tracking and Natural Language Processing 3rd Workshop on South and Southeast Asian Natural Language Processing (SANLP) Cognitive Aspects of the Lexicon (CogALex-III) 10th Workshop on Asian Language Resources 2nd Workshop on Sentiment Analysis where AI meets Psychology (SAAIP 2012) Sixth Workshop on Analytics for Noisy Unstructured Text Data
Eva Hajicova Kalika Bali, Monojit Choudhury, Yoh Okuno Michael Carl, Pushpak Bhattacharya, Kamal Kumar Choudhary Virach Sornlertlamvanich, Abbas Malik Michael Zock, Reinhard Rapp Ruvan Weerasinghe, Rachel Edita O. Roxas, Virach Sornlertlamvanich, Sarmad Hussain Sivaji Bandyopadhyay, Manabu Okumura Lipika Dey, Daniel Lopresti, Christoph Ringlstetter, Shourya Roy, L. Venkata Subramaniam
WS8
Page 41
WS9
Information Extraction & Entity Analytics on Social Media Data Machine Translation and Parsing in Indian Languages (MTPIL2012) Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT (ML4HMT-12 WS and Shared Task) Speech and Language Processing Tools in Education Reordering for Statistical Machine Translation Question Answering for Complex Domains First International Workshop on Optimization Techniques for Human Language Technology
Sriram Raghavan, Ganesh Ramakrishnan Radhika Mamidi, Ranjani Parthasarathi, Sobha Lalitha Devi, Dipti Misra Sharma, Joseph van Genabith Josef van Genabith, Toni Badia, Christian Federmann
WS10
WS11
Radhika Mamidi, Kishore Prahallad Karthik Visweswariah, Ananthakrishnan Ramanathan, Mitesh M. Khapra Nanda Kambhatla Sachindra Joshi, Ganesh Ramakrishnan, Kiran Kate, Priyanka Agrawal Pushpak Bhattacharyya, Asif Ekbal, Sriparna Saha, Mark Johnson, Diego Molla-Aliod
WS15
Page 42
Sponsored by
Diamond sponsors
Gold sponsors
Silver sponsors
Organised by
Center for Indian Language Technology, IIT Bombay Technology Development for Indian Languages