Computational Linguistics and the Information Need of Multilingual Societies

 Fifth International Workshop On "Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies"

   IJCNLP 2011 Workshop

   13 November 2011, Chiang Mai, Thailand


 First Call for Papers


Cross lingual information access (CLIA) is concerned with any technologies and applications that enable people to freely access information that is expressed in any languages. With the rapid development of globalization and digital online information in Internet, huge demand for cross lingual information access has emerged from ordinary netizens (polyglots or monoglots) who are surfing the Internet for special information (e.g. travelling, product description), and communicating in soaring social networks (e.g. Facebook, Youtube, Twitter, Myspace), to global companies which provide multilingual services to their multinational customers, and governments who aim to lower the barriers to international commerce and collaboration, and homeland security. This huge demand has triggered vigorous research and development in CLIA.


This workshop is a continuous effort to address the need of cross-lingual information access on top of its previous four issues which were held during IJCAI 2007 in Hyderabad, IJCNLP 2008 in Hyderabad, NAACL 2009 in Colorado, and COLING 2010 in Beijing. It aims to bring together researchers from a variety of fields such as information retrieval, computational linguistics, machine translation, and digital library, and practitioners from government and industry to address the issues of information need of multilingual society. We also would like to promote and emphasize the potential contributions of NLP and computational linguistic aspects to CLIA, in addition to the previously better represented viewpoint from Information Retrieval. Specifically, the key interests are in:


1. Novel methods to mine knowledge from multilingual corpora using CL and/or NLP techniques.

2. Techniques to customize machine translation in order to satisfy the special requirements of CLIA.

3. Methods to adapt the existing CL/NLP approaches in information extraction, question answering, summarization, categorization, sentiment analysis, opinion extraction from a monolingual context to a multilingual context.

4. Techniques for leveraging multilingual resources to improve the performance of monolingual information access.


We thus solicit submissions in, but not limited to, the following topics:


General CLIA:

-Approaches to cross-lingual/ multilingual information access

– Domain specific multilingual information access

– Cross-lingual cross media search (speech, video, audio)

– Machine Learning for multilingual information access  -Scalability issues in multilingual information access/ system evaluation

– Web-scale cross-lingual search


Machine translation in CLIA:


– Interaction between cross-language information retrieval and machine translation  -Query translation and document translation -Developing statistical machine translation on large-scale multilingual corpora

– Domain adaptation in machine translation

– Multilingual / Cross-lingual named entity recognition



– Multilingual summarization

– Multilingual information extraction

– Multilingual question answering

– Multilingual text categorization and clustering

– Multilingual opinion study and sentiment analysis

  -Monolingual processing leveraging on multilingual resources


CLIA evaluation and deployment:


-CLIA user studies and user-centric evaluation

– CLIA system deployment on social networks (e.g., Facebook or Twitter) or handheld computers or smartphones (e.g., iPad or iPhone)


Multilingual knowledge acquisition:

– Acquisition of multilingual parallel/comparable/non- comparable corpora

– Multilingual document/sentence/word alignment

– Multilingual lexicon/term extraction

-Multilingual new words / named entity detection and translation




Authors are invited to submit papers on original, unpublished work on the topics of this workshop. Submissions should follow the IJCNLP 2011 length and formatting requirements for long papers of eight (8) pages of contents with two (2) additional pages of references, and for short papers of two (4) pages of contents with two (2) additional pages of references. A detailed abstract with two (2) pages to address your on-going work is also welcome.



Important Dates:


June 01, 2011: Papers due


July 29, 2011: Notification of acceptance


August 19, 2011: Camera-ready deadline


November 13, 2011: Workshop





Asif Ekbal, IIT Patna, India (Co-chair)

Deyi Xiong, Institute for InfoComm Research, Singapore (Co-chair) Mitesh Khapra, IIT Bombay, India Prasenjit Majumder, DAIICT, India





Program Committee Members (to be confirmed)


Eneko Agirre University of the Basque Country Wenliang Chen Institute for Infocomm Research Sivaji Bandyopadhyay Jadavpur University Pushpak Bhattacharya IIT Bombay Nicola Cancedda Xerox Research Centre (Europe) Somnath Chandra MIT, Govt. of India Patrick Saint Dizier IRIT, Universite Paul Sabatier Nicola Ferro University of Padua Guohong Fu Heilongjiang University Cyril Goutte National Research Council of Canada Pierre Isabelle National Research Council of Canada A Kumaran Microsoft Research of India Gareth Jones Dublin City University Joemon Jose University of Glasgow Swaran Lata MIT, Govt. of India Gina-Anne Levow National Centre for Text Mining (UK) Xiangyu Duan Institute for Infocomm Research Ting Liu Harbin Institute of Technology Paul McNamee Johns Hopkins University Mandar Mitra ISI Kolkata Doug Ouard University of Maryland, College Park Carol Peters Istituto di Scienza e Tecnologie dell'Informazione and CLEF campaign Maarten de Rijke University of Amsterdam Paolo Rosso Technical University of Valencia Sudeshna Sarkar IIT Kharagpur Hendra Setiawan University of Maryland L Sobha AU-KBC, Chennai Rohini Srihari University at Buffalo, SUNY Ralf Steinberger European Commission – Joint Research Centre (Italy) Le Sun Institute of Software, CAS Chew Lim Tan National University of Singapore Raghavendra Udupa Microsoft Research Vasudeva Varma IIIT Hyderabad Thuy Vu Institute for Infocomm Research Haifeng Wang Baidu Jun Lang Institute for Infocomm Research Hao Yu Fujitsu R&D Center Co. Ltd. (China) Guodong Zhou SooChow University Chengqing Zong Institute of Automation, CAS Qun Liu Institute of Computing Technology, CAS Yang Liu Institute of Computing Technology, CAS





For any information about the workshop, please contact:

Asif Ekbal


Deyi Xiong






Effettua il login con uno di questi metodi per inviare il tuo commento:


Stai commentando usando il tuo account Chiudi sessione /  Modifica )

Google+ photo

Stai commentando usando il tuo account Google+. Chiudi sessione /  Modifica )

Foto Twitter

Stai commentando usando il tuo account Twitter. Chiudi sessione /  Modifica )

Foto di Facebook

Stai commentando usando il tuo account Facebook. Chiudi sessione /  Modifica )


Connessione a %s...