Multiword Expressions: Identification, Interpretation, Disambiguation and Applications
|Event in series||MWE|
|Subevent of||ACL/IJCNLP 2009|
|Dates||2009/08/06 (iCal) - 2009/08/06|
|Homepage:||multiword.sourceforge.net/PHITE.php?sitesig=CONF&page=CONF 40 MWE 2009 lb ACL rb|
|Camera ready due:||2009/06/07|
|Table of Contents|
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.
- 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.
- 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.
- 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.
- 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.
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/
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.
A preliminary programme for the workshop is the following:
- 09:00-09:15 Welcome and Introduction to the Workshop
Session I : Theme 1
- 09:15-09:40 : Paper 1
- 09:40-10:05 : Paper 2
- 10:05-10:30 : Paper 3
- 10:30-10:45 : Discussion of Theme 1
- 10:45-11:15 BREAK
Session II - Theme 2
- 11:15-11:40 - Paper 4
- 11:40-12:05 - Paper 5
- 12:05-12:30 - Paper 6
- 12:30-12:45 - Discussion of Theme 2
- 12:45-14:00 LUNCH
Session III - Theme 3
- 14:00-14:25 - Paper 7
- 14:25-14:50 - Paper 8
- 14:50-15:15 - Paper 9
- 15:15-15:30 - Discussion of Theme 3
- 15:30-16:00 BREAK
- 16:00-17:00 - General Discussion
- 17:00-17:15 - Closing Remarks
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
- Workshop Chair
- Program Committee Members
- 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)