First Workshop on Multilingual Modeling (MM-2012)
In conjunction with ACL 2012, Jeju Island, Republic of Korea
http://mm2012.weebly.com/
==================================================
The burgeoning community of multilingual users poses variety of new problems and also enables new opportunities. The large number of multilingual corpora requires effective and scalable ways for organizing them. This additional data in different languages provides a different perspective. Resource poor languages can utilize the training data available in other languages and improve the accuracies of monolingual applications.
Recently, we have seen an increasing number of researchers working on multilingual problems varying from mining comparable corpora from the web to multilingual part-of-speech tagging. It is encouraging to see how the abundant training data in a resource rich languages (such as English) is used along with very little training data in the target language to solve problems in resource-poor languages. In addition, resource rich languages have been used successfully to bridge the language barrier between two resource poor languages.
In this workshop, we aim to bring researchers working on different aspects of multilingualism to a common ground to share their experiences so that the entire community can benefit. The topics of interest to this workshop include, but are not limited to:
Mining Comparable Corpora
Mining for comparable corpora from the web
Learning lexicons from comparable/non-parallel corpora
SMT using non-parallel corpora
Modeling Comparable Corpora to Enable Cross-lingual Knowledge Transfer
Learning Interlingual representations
Bilingual Projections
Document Alignment (or Mate Retrieval)
Improving Monolingual Applications using Multilingual Data
Multilingual POS tagging
Multilingual Dependency Parsing
Multilingual WSD
Transliteration across Multiple Languages
Multilingual NE Mining
Multilingual Sentiment Classification
Multilingual Information Retrieval
Multilingual Speech Recognition
Multilingual Pronunciation Modeling
Bridge Language Approaches
Standardization of Annotations across Languages
Important Dates :
Paper Submission : Apr 25, 2012
Paper Acceptance Notification : May 10, 2012
Camera Ready Submission : May 18, 2012
Workshop Date : Jul 13, 2012
Submissions :
Submissions must describe original, high quality and unpublished work. Submissions may consist of up to six (6) pages of content and unlimited number of references. Papers should be formatted according to the ACL 2012 guidelines. Papers that have been submitted to other venues must provide this information during the submission, but upon acceptance, the authors should specify which conference they choose for presentation of their work. Papers must be submitted using the submission page at the following url: https://www.softconf.com/acl2012/mm-2012/ Please visit the workshop web page (http://mm2012.weebly.com/) for more details.
Organizers :
Jagadeesh Jagarlamudi (University of Maryland, USA)
Sujith Ravi (Google, USA)
Xiaojun Wan (Peking University, China)
Hal Daumé III (University of Maryland, USA)
Program Committee :
Kumaran A (Microsoft Research, India)
Pushpak Bhattacharyya (Indian Institute of Technology, India)
Srinivas Bangalore (AT&T Labs-Research, USA)
Hal Daume III (University of Maryland, USA)
Kareem Darwish (Qatar Computing Research Institute, Qatar)
Dipanjan Das (Carnegie Mellon University, USA)
Marcello Federico (FBK -- Fondazione Bruno Kessler, Tirento, Italy)
Anna Feldman (Montclair State University, USA)
Wei Gao (Qatar Computing Research Institute, Qatar)
Jagadeesh Jagarlamudi (University of Maryland, USA)
Heng Ji (City University of New York)
Mitesh Khapra (Indian Institute of Technology, India)
Alexandre Klementiev (Saarland University, USA)
Kevin Knight (USC/ISI, USA)
Yang Liu (Tsinghua University, China)
Paul McNamee (Johns Hopkins University, USA)
Rada Mihalcea (University of North Texas, USA)
Xiaochuan Ni (Microsoft)
Doug Oard (University of Maryland, USA)
Reinhard Rapp (Johannes Gutenberg-Universität Mainz, Germany)
Ari Rappoport (The Hebrew University, Israel)
Sujith Ravi (Google, USA)
Benjamin Snyder (University of Wisconsin-Madison, USA)
Benno Stein (Bauhaus-Universität Weimar, Germany)
Sebastian Stüker (Karlsruhe Institute of Technology, Germany)
Jun'ichi Tsujii (Microsoft Research Asia)
Kentaro Torisawa (NICT, Japan)
Raghavendra Udupa (Microsoft Research, India)
Xiaojun Wan (Peking University, China)
Mausam (University of Washington, USA)
Contact Information :
mm-2012 [(put at)] googlegroups ([put dot]) com
In conjunction with ACL 2012, Jeju Island, Republic of Korea
http://mm2012.weebly.com/
==================================================
The burgeoning community of multilingual users poses variety of new problems and also enables new opportunities. The large number of multilingual corpora requires effective and scalable ways for organizing them. This additional data in different languages provides a different perspective. Resource poor languages can utilize the training data available in other languages and improve the accuracies of monolingual applications.
Recently, we have seen an increasing number of researchers working on multilingual problems varying from mining comparable corpora from the web to multilingual part-of-speech tagging. It is encouraging to see how the abundant training data in a resource rich languages (such as English) is used along with very little training data in the target language to solve problems in resource-poor languages. In addition, resource rich languages have been used successfully to bridge the language barrier between two resource poor languages.
In this workshop, we aim to bring researchers working on different aspects of multilingualism to a common ground to share their experiences so that the entire community can benefit. The topics of interest to this workshop include, but are not limited to:
Mining Comparable Corpora
Mining for comparable corpora from the web
Learning lexicons from comparable/non-parallel corpora
SMT using non-parallel corpora
Modeling Comparable Corpora to Enable Cross-lingual Knowledge Transfer
Learning Interlingual representations
Bilingual Projections
Document Alignment (or Mate Retrieval)
Improving Monolingual Applications using Multilingual Data
Multilingual POS tagging
Multilingual Dependency Parsing
Multilingual WSD
Transliteration across Multiple Languages
Multilingual NE Mining
Multilingual Sentiment Classification
Multilingual Information Retrieval
Multilingual Speech Recognition
Multilingual Pronunciation Modeling
Bridge Language Approaches
Standardization of Annotations across Languages
Important Dates :
Paper Submission : Apr 25, 2012
Paper Acceptance Notification : May 10, 2012
Camera Ready Submission : May 18, 2012
Workshop Date : Jul 13, 2012
Submissions :
Submissions must describe original, high quality and unpublished work. Submissions may consist of up to six (6) pages of content and unlimited number of references. Papers should be formatted according to the ACL 2012 guidelines. Papers that have been submitted to other venues must provide this information during the submission, but upon acceptance, the authors should specify which conference they choose for presentation of their work. Papers must be submitted using the submission page at the following url: https://www.softconf.com/acl2012/mm-2012/ Please visit the workshop web page (http://mm2012.weebly.com/) for more details.
Organizers :
Jagadeesh Jagarlamudi (University of Maryland, USA)
Sujith Ravi (Google, USA)
Xiaojun Wan (Peking University, China)
Hal Daumé III (University of Maryland, USA)
Program Committee :
Kumaran A (Microsoft Research, India)
Pushpak Bhattacharyya (Indian Institute of Technology, India)
Srinivas Bangalore (AT&T Labs-Research, USA)
Hal Daume III (University of Maryland, USA)
Kareem Darwish (Qatar Computing Research Institute, Qatar)
Dipanjan Das (Carnegie Mellon University, USA)
Marcello Federico (FBK -- Fondazione Bruno Kessler, Tirento, Italy)
Anna Feldman (Montclair State University, USA)
Wei Gao (Qatar Computing Research Institute, Qatar)
Jagadeesh Jagarlamudi (University of Maryland, USA)
Heng Ji (City University of New York)
Mitesh Khapra (Indian Institute of Technology, India)
Alexandre Klementiev (Saarland University, USA)
Kevin Knight (USC/ISI, USA)
Yang Liu (Tsinghua University, China)
Paul McNamee (Johns Hopkins University, USA)
Rada Mihalcea (University of North Texas, USA)
Xiaochuan Ni (Microsoft)
Doug Oard (University of Maryland, USA)
Reinhard Rapp (Johannes Gutenberg-Universität Mainz, Germany)
Ari Rappoport (The Hebrew University, Israel)
Sujith Ravi (Google, USA)
Benjamin Snyder (University of Wisconsin-Madison, USA)
Benno Stein (Bauhaus-Universität Weimar, Germany)
Sebastian Stüker (Karlsruhe Institute of Technology, Germany)
Jun'ichi Tsujii (Microsoft Research Asia)
Kentaro Torisawa (NICT, Japan)
Raghavendra Udupa (Microsoft Research, India)
Xiaojun Wan (Peking University, China)
Mausam (University of Washington, USA)
Contact Information :
mm-2012 [(put at)] googlegroups ([put dot]) com