LINGUIST List 22.19|
Tue Jan 04 2011
Calls: Cognitive Science, Computational Ling/USA
Editor for this issue: Amy Brunett
LINGUIST is pleased to announce the launch of an exciting new feature: Easy Abstracts! Easy Abs is a free abstract submission and review facility designed to help conference organizers and reviewers accept and process abstracts online. Just go to: http://www.linguistlist.org/confcustom, and begin your conference customization process today! With Easy Abstracts, submission and review will be as easy as 1-2-3!
1. Aline Villavicencio ,
ACL 2011 Workshop on Multiword Expressions
Message 1: ACL 2011 Workshop on Multiword Expressions
From: Aline Villavicencio <alinevgmail.com>
Subject: ACL 2011 Workshop on Multiword Expressions
E-mail this message to a friend
Full Title: ACL 2011 Workshop on Multiword Expressions
Short Title: ACL 2011 MWE Workshop
Date: 23-Jun-2011 - 23-Jun-2011
Location: Portland, USA
Contact Person: Carlos Ramisch
Meeting Email: < click here to access email >
Web Site: http://multiword.sf.net/mwe2011
Linguistic Field(s): Cognitive Science; Computational Linguistics
Call Deadline: 04-Mar-2011
ACL 2011 Workshop on Multiword Expressions: from Parsing and Generation to the real world (MWE 2011)
Endorsed by the Special Interest Group on the Lexicon of the Association for Computational Linguistics (SIGLEX)
Portland, Oregon, USA - June 23-24, 2011
Submission deadline: Mar 4, 2011 at 23:59 PDT (GMT-7)
Under the denomination 'Multiword Expression', one can hang a wide range of linguistic constructions such as idioms (a frog in the throat, kill some time), fixed phrases (per se, by and large, rock'n roll), noun compounds (telephone booth, cable car), compound verbs (give a presentation, go by [a name]), etc. While easily mastered by native speakers, their interpretation poses a major challenge for computational systems, due to their flexible and heterogeneous nature. Surprisingly enough, MWEs are not nearly as frequent in NLP resources (dictionaries, grammars) as they are in real-word text, where they have been reported to account for over 70% of the terms in a domain. Thus, MWEs are a key issue and a current weakness for tasks like Natural Language Parsing (NLP) and Generation (NLG), as well as real-life applications such as Machine Translation.
MWE 2011 will be the 8th event in the series, and the time has come to move from basic preliminary research and theoretical results to actual applications in real-world NLP tasks. Therefore, following further the trend of previous MWE workshops, we propose a turn towards MWEs on NLP applications, specifically towards Parsing and Generation of MWEs, as there is a wide range of open problems that prevent MWE treatment techniques to be fully integrated in current NLP systems. We will be asking for original research related (but not limited) to the following topics:
Lexical representations: In spite of several proposals for MWE representation ranging along the continuum from words-with-spaces to compositional approaches connecting lexicon and grammar, to date, it remains unclear how MWEs should be represented in electronic dictionaries, thesauri and grammars. New methodologies that take into account the type of MWE and its properties are needed for efficiently handling manually and/or automatically acquired expressions in NLP systems. Moreover, we also need strategies to represent deep attributes and semantic properties for these multiword entries.
Application-oriented evaluation: Evaluation is a crucial aspect for MWE research. Various evaluation techniques have been proposed, from manual inspection of top-n candidates to classic precision/recall measures. However, only application-oriented techniques can give a clear indication of whether the acquired MWEs are really useful. We call for submissions that study the impact of MWE handling in applications such as Parsing, Generation, Information Extraction, Machine Translation, Summarization, etc.
Type-dependent analysis: While there is no unique definition or classification of MWEs, most researchers agree on some major classes such as named entities, collocations, multiword terminology and verbal expressions. These, though, are very heterogeneous in terms of syntactic and semantic properties, and should thus be treated differently by applications. Type-dependent analyses could shed some light on the best methodologies to integrate MWE knowledge in our analysis and generation systems.
MWE engineering: Where do my MWEs go after being extracted? Do they belong to the lexicon and/or to the grammar? In the pipeline of linguistic analysis and/or generation, where should we insert MWEs? And even more important: How? Because all the effort put in automatic MWE extraction will not be useful if we do not know how to employ these rich resources in our real-life NLP applications!
Call for Papers:
MWE 2011 introduces three different submission modalities:
Regular long papers (8 content pages + 1 page for references):
Long papers should report on solid and finished research including new experimental results, resources and/or techniques.
Regular short papers (4 content pages + 1 page for references):
Short papers should report on small experiments, focused contributions, ongoing research, negative results and/or philosophical discussion.
System demonstration (2 pages):
System demonstration papers should describe and document the demonstrated system or resources. We encourage the demonstration of both early research prototypes and mature systems that will be presented in a separate demo session.
All submissions must be in PDF format and must follow the ACL 2011 formatting requirements (available at http://www.acl2011.org/call.shtml#submission). We strongly advise the use of the provided Word or LaTeX template files. For regular long and short papers, the reported research should be substantially original. The papers will be presented orally or as posters. The decision as to which paper will be presented orally and which as poster will be made by the program committee based on the nature rather than on the quality of the work.
Following the example of major conferences like ACL-HLT 2011, this year we will also accept papers accompanied by the resource (software or data) described in the paper. Resources will be reviewed separately and the final acceptance decision will be made based on both the resource reviews and the paper reviews. The software or data resources submitted should be ready for release and should contain at a README file. All resources will be made available to the MWE community.
Reviewing will be double-blind, and thus no author information should be included in the papers; self-reference should be avoided as well. Resources submitted with the papers should be anonymized for submission. Papers and/or resources that do not conform to these requirements will be rejected without review. Accepted papers will appear in the workshop proceedings, where no distinction will be made between papers presented orally or as posters.
More details about the submission procedure (e.g. online submission system) will be available soon.
Mar 4, 2011: Long paper submission deadline 23:59 PDT (GMT-7)
Mar 11, 2011: Short paper and demo submission deadline 23:59 PDT (GMT-7)
Apr 15, 2011: Notification of acceptance
Apr 22, 2011: Camera-ready deadline
Jun 23-24, 2011: Workshop (to be confirmed by ACL)
Iñaki Alegria (University of the Basque Country, Spain)
Dimitra Anastasiou (University of Bremen, Germany)
Timothy Baldwin (University of Melbourne, Australia)
Srinivas Bangalore (AT&T Labs-Research, USA)
Francis Bond (Nanyang Technological University, Singapore)
Aoife Cahill (IMS University of Stuttgart, Germany)
Paul Cook (University of Toronto, Canada)
Béatrice Daille (Nantes University, France)
Mona Diab (Columbia University, USA)
Gael Dias (Beira Interior University, Portugal)
Stefan Evert (University of Osnabrueck, Germany)
Roxana Girju (University of Illinois at Urbana-Champaign, USA)
Chikara Hashimoto (National Institute of Information and Communications Technology, Japan)
Ulrich Heid (Stuttgart University, Germany)
Kyo Kageura (University of Tokyo, Japan)
Adam Kilgarriff (Lexical Computing Ltd., UK)
Anna Korhonen (University of Cambridge, UK)
Ioannis Korkontzelos (University of Manchester, UK)
Zornitsa Kozareva (University of Southern California, USA)
Brigitte Krenn (Austrian Research Institute for Artificial Intelligence, Austria)
Takuya Matsuzaki (University of Tokyo, Japan)
Diana McCarthy (Lexical Computing Ltd., UK)
Yusuke Miyao (National Institute of Informatics, Japan)
Rosamund Moon (University of Birmingham, UK)
Diarmuid Ó Séaghdha (University of Cambridge, UK)
Jan Odijk (University of Utrecht, The Netherlands)
Darren Pearce-Lazard (University of Sussex, UK)
Pavel Pecina (Dublin City University, Ireland)
Scott Piao (Lancaster University, UK)
Elisabete Ranchhod (University of Lisbon, Portugal)
Barbara Rosario (Intel Labs, USA)
Agata Savary (Université François Rabelais Tours, France)
Violeta Seretan (University of Edinburgh, UK)
Suzanne Stevenson (University of Toronto, Canada)
Sara Stymne (Linköping University, Sweden)
Stan Szpakowicz (University of Ottawa, Canada)
Beata Trawinski (University of Vienna, Austria)
Vivian Tsang (Bloorview Research Institute, Canada)
Kyioko Uchiyama (National Institute of Informatics, Japan)
Ruben Urizar (University of the Basque Country, Spain)
Gertjan van Noord (University of Groningen, The Netherlands)
Tony Veale (University College Dublin, Ireland)
Begoña Villada Moirón (Q-go, The Netherlands)
Yi Zhang (DFKI GmbH & Saarland University, Germany)
Su Nam Kim (University of Melbourne, Australia)
Preslav Nakov (National University of Singapore, Singapore)
Workshop Organizers and Contact:
Valia Kordoni (Saarland University, Germany)
Carlos Ramisch (University of Grenoble, France and Federal University of Rio Grande do Sul, Brazil)
Aline Villavicencio (Federal University of Rio Grande do Sul, Brazil)
For any inquiries regarding the workshop please send an email to mwe2011 at gmail.com
Read more issues|LINGUIST home page|Top of issue
Page Updated: 04-Jan-2011
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed
on its pages, it cannot vouch for their contents.