Home‎ > ‎

Call for Papers

WLM 2012: NAACL-HLT 2012 Workshop on the Future of Language Modeling for HLT
Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT.

WLM 2012 is co-located with the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2012). It will take place in Montreal, Quebec, Canada on June 8, 2012.

Important Dates:
Paper Deadline: March 26, 2012 April 6, 2012
Author Notification: April 23, 2012 May 2, 2012
Camera-ready Papers: May 4, 2012 May 6, 2012
Workshop: June 8, 2012

Description of the workshop topic and content:
Language models are a critical component in many speech and natural language processing technologies, such as speech recognition and understanding, voice search, conversational interaction and machine translation. Over the last few decades, several advanced language modeling ideas have been proposed. Some of these approaches have focused on incorporating linguistic information such as syntax and semantics whereas others have focused on fundamental modeling and parameter estimation techniques. Although tremendous progress has been made in language modeling, n-grams are still very much the state-of-the-art due to the simplicity of the model and strong recognition performance.

The aim of this workshop is to bring together researchers from NLP, linguistics, spoken language processing and machine learning and to provide a venue to explore and discuss new approaches to language modeling for different applications. In this workshop, we hope to encourage a lively interaction amongst various groups that will push the frontier of language modeling even further.

The workshop topics include, but are not limited to:
- Advanced parameter estimation for language modeling
- Unsupervised and semi-supervised language modeling 
- Exploiting higher-level linguistic information into language modeling 
- Exploiting acoustic information into language modeling
- Utilizing meta-data in language modeling
- Language modeling for diverse tasks and applications: summarization, rephrasing

Submission Details:
Authors are invited to submit long or short papers on original and unpublished work related to the workshop topics. Long papers may consist of up to 8 pages of content plus two extra pages for references; short papers may consist of 4 pages of content including references. Papers should be formatted according to the NAACL 2012 guidelines (for more information please visit http://www.naaclhlt2012.org/conference/conference.php).

Submission is electronic using the Softconf submission software at https://www.softconf.com/naaclhlt2012/WLM2012/

Organizing Committee: 
Bhuvana Ramabhadran (IBM T.J. Watson Research Center)
Sanjeev Khudanpur (Johns Hopkins University)
Ebru Arisoy (IBM T.J. Watson Research Center)

Program Committee:
Ciprian Chelba (Google)
Stanley F. Chen (IBM T.J. Watson Research Center)
Ahmad Emami (IBM T.J. Watson Research Center)
Tomas Mikolov (Brno University of Technology)
Hermann Ney (RWTH Aachen University)
Kemal Oflazer (Carnegie Mellon University - Qatar)
Brian Roark (Oregon Health and Science University)
Murat Saraclar (Bogazici University)
Holger Schwenk (University of LIUM)
Peng Xu (Google)
Geoffrey Zweig (Microsoft)