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