[Corpora-List] ACL-2004 Workshop on Multiword Expressions (Call for Participation)

From: bond@cslab.kecl.ntt.co.jp
Date: Wed Jun 30 2004 - 11:20:53 MET DST

  • Next message: Alberto Lavelli: "[Corpora-List] annotation tools"

                      ***** Call for Participation *****

    2nd Workshop on Multiword Expressions: Integrating Processing

    A Workshop in conjunction with ACL'04 in Barcelona, Spain

    --------------------------------------------------------------------
    Workshop date: July 26, 2004
    Workshop website: http://www.cl.cam.ac.uk/users/alk23/mwe04/mwe.html
    --------------------------------------------------------------------

    To register for the workshop, go to http://www.acl2004.org/

    WORKSHOP OVERVIEW:

    In recent years, there has been a growing awareness in the NLP
    community of the problems that Multiword Expressions (MWEs) pose and
    the need for their robust handling. MWEs include a large range of
    linguistic phenomena, such as phrasal verbs (e.g. "add up"), nominal
    compounds (e.g. "telephone box"), and institutionalized phrases
    (e.g. "salt and pepper"). These expressions, which can be
    syntactically and/or semantically idiosyncratic in nature, are used
    frequently in everyday language, usually to express precisely ideas
    and concepts that cannot be compressed into a single word.

    Many real-world applications tend to ignore MWEs or address them
    simply by listing. However, it is clear that successful applications
    will need to be able to identify and treat them appropriately. This
    particularly applies to the many applications which require some
    degree of semantic interpretation (e.g. machine translation,
    question-answering, summarisation, generation) and require tasks such
    as parsing and word sense disambiguation.

    In this workshop the focus is on papers that integrate analysis,
    acquisition and treatment of various kinds of multiword expressions
    (MWEs) in NLP. For example,

    (1) research that combines a linguistic analysis with a method of
        automatically acquiring the classes described

    (2) work that combines the computational treatment of a class of MWEs
        with a solid linguistic analysis

    (3) research that extracts MWEs and either classifies them or uses
        them in some task.

    These combinations of research will help to bridge the gap between the
    needs of NLP and the descriptive tradition of linguistics.

    WORKSHOP PROGRAM:

      9:30-9:35 Welcome
              
      9:35-10:00 * Statistical Measures of the Semi-Productivity of
                    Light Verb Constructions
                  - Suzanne Stevenson, Afsaneh Fazly and Ryan North

      10:00-10:25 * Paraphrasing of Japanese Light-verb Constructions
                    Based on Lexical Conceptual Structure
                  - Atsushi Fujita, Kentaro Furihata, Kentaro Inui,
                    Yuji Matsumoto and Koichi Takeuchi

      10:25-10:50 * What is at Stake: a Case Study of Russian Expressions
                    Starting with a Preposition
                  - Serge Sharoff

      10:50-11:20 BREAK
              
      11:20-11:45 * Translation by Machine of Complex Nominals: Getting it Right
                  - Timothy Baldwin and Takaaki Tanaka

      11:45-12:10 * MWEs as Non-propositional Content Indicators
                  - Kosho Shudo, Toshifumi Tanabe, Masahito Takahashi and
                    Kenji Yoshimura

      12:10-12:35 * Multiword Expression Filtering for Building Knowledge
                  - Shailaja Venkatsubramanyan and Jose Perez-Carballo

      12:35-14:00 LUNCH
              
      14:00-14:25 * Representation and Treatment of Multiword Expressions
                  in Basque
                  - Inaki Alegria, Olatz Ansa, Xabier Artola,
                    Nerea Ezeiza, Koldo Gojenola and Ruben Urizar

      14:25-14:50 * Multiword Expressions as Dependency Subgraphs
                  - Ralph Debusmann

      14:50-15:15 * Integrating Morphology with Multi-word Expression
                    Processing in Turkish
                  - Kemal Oflazer, Ozlem Cetinoglu and Bilge Say

      15:15-15:45 BREAK
              
      15:45-16:10 * Frozen Sentences of Portuguese: Formal Descriptions for NLP
                  - Jorge Baptista, Anabela Correia and Graca Fernandes

      16:10-16:35 * Lexical Encoding of MWEs
                  - Aline Villavicencio, Ann Copestake, Benjamin Waldron
                    and Fabre Lambeau

      16:35-17:30 DISCUSSION

    ORGANIZING COMMITTEE:

        Takaaki Tanaka (NTT Communication Science Laboratories, Japan)
        Aline Villavicencio (University of Essex, UK; University of Cambridge, UK)
        Francis Bond (NTT Communication Science Laboratories, Japan)
        Anna Korhonen (University of Cambridge, UK)

    PROGRAM COMMITTEE:

        Timothy Baldwin (Stanford University, USA)
        Colin Bannard (University of Edinburgh, UK)
        Gael Dias (Beira Interior University, Portugal)
        James Dowdall (University of Zurich, Switzerland)
        Dan Flickinger (Stanford University, USA)
        Matthew Hurst (Intelliseek, USA)
        Stephan Oepen (Stanford University, USA; University of Oslo, Norway)
        Kyonghee Paik (ATR Spoken Language Translation Research Laboratories, Japan)
        Scott Piao (University of Lancaster, UK)
        Beata Trawinski (University of Tuebningen, Germany)
        Kiyoko Uchiyama (Keio University, Japan)

    CONTACT: mwe-acl04@cl.cam.ac.uk

    --------------------------------------------------------------------



    This archive was generated by hypermail 2b29 : Thu Jul 01 2004 - 07:39:35 MET DST