[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[eu_members at aclweb dot org] Singapore: ACL/IJCNLP 2009 Workshop on Multiword Expressions (MWE 2009) -- Final CFP



Multiword Expressions: Identification, Interpretation, Disambiguation 
and Applications (MWE 2009)
Workshop at the ACL/IJCNLP 2009 Conference (Singapore), 06 August 2009

Endorsed by the ACL Special Interest Group on the Lexicon (SIGLEX)

Description

       Multi-Word Expressions (MWEs) are an indispensable part of 
natural languages and appear steadily on a daily basis, both new and 
already existing but paraphrased. Thus, the automated processing of 
MWEs is important for many natural language applications. The meaning 
of MWEs can be either motivated or arbitrary. Native speakers master 
most MWEs, while learners of a foreign language have to learn MWEs by 
heart. The interpretation of MWEs poses a major challenge for 
automated analysis helping both groups easily master MWEs.

       The growing interest in MWEs in the NLP community has led to 
many specialized workshops held every year since 2001 in conjunction 
with ACL, EACL and LREC; there have been also two recent special 
issues on MWEs published by leading journals: the International 
Journal of Language Resources and Evaluation, and the Journal of 
Computer Speech and Language.

       As a result of the overall progress in the field, the time has 
come to move from basic preliminary research to actual applications in 
real-world NLP tasks. Following this trend, the LREC-MWE'08 focused on 
gathering resources and creating a common repository in order to rank 
MWE candidates and facilitate further research.

Call for papers

       In MWE'09 we are interested in the overall process of dealing 
with MWEs, asking for original research related (but not limited) to 
the following four fundamental topics.

       Workshop topics
             (1) Identification. Identification is a major problem for 
MWEs. The MWE identification task is to determine whether a MWE is 
used non-compositionally (figuratively) or compositionally (literally) 
in a particular context. The identification of MWEs by automated means 
is a difficult task, as it does not suffice to store the MWE into a 
dictionary database. Rule-based (morphosyntactic rules) and/or 
statistical approaches may be needed to identify MWEs in context.

             (2) Interpretation. Semantic interpretation of MWEs, 
particularly noun compounds and determinerless prepositional phrases, 
is the task of determining the implicit semantic relation holding 
between the MWE's sub-components. This specific area is inviting 
research on (linguistically) identifying the semantic relations (SRs) 
and automatic SR interpretation in MWEs. The relation inventories used 
can be of different granularity and dependent on the particular type 
of MWE construction. In some cases, MWE's semantics can be also 
specified in terms of a suitable paraphrase.

             (3) Disambiguation. Disambiguation (Semantic 
classification) is the task of specifying the semantics of MWEs based 
on an inventory of semantic relations. It tends to presuppose the 
ability to classify the (degree of) compositionality of MWEs and 
applies only to compositional MWEs. The aim is to specify the 
semantics of MWEs in terms of predefined semantic categories, e.g., in 
WordNet.

             (4) Applications. Identifying MWEs in context and 
understanding their syntax and semantics is important for many natural 
language applications, including but not limited to question 
answering, machine translation, information retrieval, information 
extraction, and textual entailment. Still, despite the growing 
research interest, there are not enough successful applications in 
real NLP problems, which we believe is the key for the advancement of 
the field.

       Submission information
             Submissions must describe substantial, original, and 
unpublished work. Submissions will be judged on correctness, 
originality, technical strength, significance and relevance to the 
conference, and interest to the attendees. Full papers may consist of 
up to eight (8) pages in total (references icluded) and will be 
presented orally. The deadline for paper submission is May 1, 2009 
(GMT + 8).
             The official style files for ACL/IJCNLP 2009 are available at:
             http://www.acl-ijcnlp-2009.org/main/authors/stylefiles/.
             The workshop submissions should use the same formatting 
guidelines. As the reviewing will be blind, the paper must not include 
the authors' names and affiliations. Furthermore, self-references that 
reveal the author's identity, e.g., "We previously showed (Smith, 
1991) ...", must be avoided. Instead, use citations such as "Smith 
previously showed (Smith, 1991) ...". Papers that do not conform to 
these requirements will be rejected without review.
             Submission is electronic using paper submission software at:
             https://www.softconf.com/acl-ijcnlp09/MWE/

Length and Format of Workshop

       The desirable duration of the workshop is one full day. Each 
session will consist of three slots for original papers; the 
presentations will be categorized in one of the three sessions 
according to their topic. Each speaker will be given 20 minutes for 
the presentation and 5 minutes for questions. Each session will 
conclude with a 15 minute discussion on important issues brought up by 
the presentations or concerning the session's theme.

       At the end of the workshop, we will have one hour of general 
discussion and closing remarks. In this hour, the participants will 
have the opportunity to elaborate on general questions related both to 
the topics of the workshop's sessions, the current state of research 
on MWEs and future prospects.


Important dates

       Paper submission deadline         May 1, 2009
       Notification of acceptance of papers June 1, 2009
       Camera-ready copies due                 June 7, 2009
       ACL-IJCNLP 2009 Workshops         August 6-7, 2009

Programme committee

     * Inaki Alegria, University of the Basque Country (Spain)
     * Timothy Baldwin, Stanford University (USA); University of 
Melbourne (Australia)
     * Colin Bannard, Max Planck Institute (Germany)
     * Francis Bond, National Institute of Information and 
Communications Technology (Japan)
     * Gael Dias, Beira Interior University (Portugal)
     * Ulrich Heid, Stuttgart University (Germany)
     * Stefan Evert, University of Osnabrueck (Germany)
     * Afsaneh Fazly,University of Toronto (Canada)
     * Nicole Gregoire,University of Utrecht (The Netherlands)
     * Roxana Girju,University of Illinois at Urbana-Champaign (USA)
     * Kyo Kageura, University of Tokyo (Japan)
     * Brigitte Krenn, Austrian Research Institute for Artificial 
Intelligence (Austria)
     * Eric Laporte, University of Marne-la-Vall?e (France)
     * Rosamund Moon, University of Birmingham (UK)
     * Diana McCarthy, University of Sussex (UK)
     * Jan Odijk, University of Utrecht (The Netherlands)
     * Stephan Oepen, Stanford University (USA); University of Oslo (Norway)
     * Darren Pearce, London Knowledge Lab (UK)
     * Pavel Pecina, Charles University (Czech Republic)
     * Scott Piao, University of Manchester (UK)
     * Violeta Seretan, University of Geneva (Switzerland)
     * Suzanne Stevenson, University of Toronto (Canada)
     * Stan Szpakowicz, University of Ottawa (Canada)
     * Beata Trawinski, University of Tuebingen (Germany)
     * Peter Turney, National Research Council of Canada (Canada)
     * Kiyoko Uchiyama, Keio University (Japan)
     * Begona Villada Moiron, University of Groningen (The Netherlands)
     * Aline Villavicencio, Federal University of Rio Grande do Sul (Brazil)

Workshop chairs

     * Dimitra Anastasiou, Localisation Research Centre, Limerick 
University, Ireland
     * Chikara Hashimoto, National Institute of Information and 
Communications Technology, Japan
     * Preslav Nakov, National University of Singapore, Singapore
     * Su Nam Kim, University of Melbourne, Australia

Contact

       For any inquiries regarding the workshop please contact Dimitra 
Anastasiou.