Call for Participation ==========================================
The 10th Workshop on Multiword Expressions (MWE 2014)
Workshop at EACL 2014 (Gothenburg, Sweden), April 26-27, 2014
Endorsed by the Special Interest Group on the Lexicon of the Association for Computational Linguistics (SIGLEX) SIGLEX's Multiword Expressions Section (SIGLEX-MWE), and PARSEME, European IC1207 COST Action
Invited Speakers: Preslav Nakov, Qatar Computing Research Institute (Qatar) Ekaterina Shutova, ICSI, UC Berkeley (USA) One more invited speaker: TBC
Workshop website: http://multiword.sourceforge.net/mwe2014/
Registration: http://eacl2014.org/registration ----------------------------------------------------------- The Workshop on Multiword Expressions (MWE 2014) is the tenth anniversary edition of related workshops which have been held almost every year since 2003 in conjunction with ACL, EACL, NAACL, COLING and LREC.
The workshop provides an important venue for interaction, sharing of resources and tools and collaboration efforts for advancing the computational treatment of Multiword Expressions (MWEs). The workshop is targeted at anyone working on a variety of languages and MWE types.
MWEs include idioms (storm in a teacup, sweep under the rug), fixed phrases (in vitro, by and large, rock’n roll), noun compounds (olive oil, laser printer), compound verbs (take a nap, bring about), among others. These, while easily mastered by native speakers, are a key issue and a current weakness for natural language parsing and generation, as well as real-life applications depending on some degree of semantic interpretation, such as machine translation, just to name a prominent one among many. However, thanks to the joint efforts of researchers from several fields working on MWEs, significant progress has been made in recent years, especially concerning the construction of large-scale language resources. For instance, there is a large number of recent papers that focus on acquisition of MWEs from corpora, and others that describe a variety of techniques to find paraphrases for MWEs. Current methods use a plethora of tools such as association measures, machine learning, syntactic patterns, web queries, etc.
This year’s tenth anniversary edition of the MWE workshop is also supported by the IC1207 COST action PARSEME dedicated to Parsing and Multiword Expressions. This European initiative, which started in 2013, gathers 29 European COST member countries, one COST cooperating state and 3 non-COST institutions from the USA and Brazil. Its objective is to increase and enhance the information and communication technology support of the European multilingual heritage by bringing about a substantial progress in the understanding and modelling of MWEs within advanced multilingual NLP techniques, notably deep parsing.
WORKSHOP PROGRAMME
Saturday, April 26, 2014
8:45–9:00 Opening Remarks
09:00-10:00 Oral Session 1: Detection and Extraction of MWEs
9:00–9:30 Breaking Bad: Extraction of Verb-Particle Constructions from a Parallel Subtitles Corpus Aaron Smith
9:30–10:00 A Supervised Model for Extraction of Multiword Expressions, Based on Statistical Context Features Meghdad Farahmand and Ronaldo Martins
10:00-10:30 Oral Session 2: PARSEME I – Parsing MWEs
10:00–10:30 VPCTagger: Detecting Verb-Particle Constructions With Syntax-Based Methods István Nagy T. and Veronika Vincze
10:30–11:00 Coffee Break
11:00–12:00 Invited Talk 1: Preslav Nakov - Title "The Web as an Implicit Training Set: Application to Noun Compounds Syntax and Semantics"
12:00-12:30 Oral Session 2: PARSEME I – Parsing MWEs (continued)
12:00–12:30 The Relevance of Collocations for Parsing Eric Wehrli
12:30–14:00 Lunch
14:00-15:00 Oral Session 3: Short papers – PARSEME II
14:00–14:20 Parsing Modern Greek verb MWEs with LFG/XLE grammars Niki Samaridi and Stella Markantonatou
14:20–14:40 Evaluation of a Substitution Method for Idiom Transformation in Statistical Machine Translation Giancarlo Salton, Robert Ross and John Kelleher
14:40–15:00 Encoding MWEs in a conceptual lexicon Aggeliki Fotopoulou, Stella Markantonatou and Voula Giouli
15:00–15:30 Poster Booster Session (4 minutes per poster)
German Compounds and Statistical Machine Translation. Can they get along? Carla Parra Escartín, Stephan Peitz and Hermann Ney
Extracting MWEs from Italian corpora: A case study for refining thePOS-pattern methodology Sara Castagnoli, Malvina Nissim and Francesca Masini
Mickey Mouse is not a Phrase: Improving Relevance in E-Commerce with Multiword Expressions Prathyusha Senthil Kumar, Vamsi Salaka, Tracy Holloway King and Brian Johnson
Encoding of Compounds in Swedish FrameNet Karin Friberg Heppin and Miriam R L Petruck
Extraction of Nominal Multiword Expressions in French Marie Dubremetz and Joakim Nivre
Towards an Empirical Subcategorization of Multiword Expressions Luigi Squillante
Contexts, Patterns, Interrelations - New Ways of Presenting Multi-word Expressions Kathrin Steyer and Annelen Brunner
Detecting change and emergence for multiword expressions Martin Emms and Arun Jayapal
An Approach to Take Multi-Word Expressions Claire Bonial, Meredith Green, Jenette Preciado and Martha Palmer
15:30–16:00 Coffee Break
16:00–17:30 Poster Session
Sunday, April 27, 2014
9:30–10:30 Invited Talk 2: TBA
10:30–11:00 Coffee Break
11:00-12:00 Oral Session 5: Short papers – MWEs in multilingual applications
11:00–11:20 Paraphrasing Swedish Compound Nouns in Machine Translation Edvin Ullman and Joakim Nivre
11:20–11:40 Feature Norms of German Noun Compounds Stephen Roller and Sabine Schulte im Walde
11:40–12:00 Identifying collocations using cross-lingual association measures Lis Pereira, Elga Strafella, Kevin Duh and Yuji Matsumoto
12:00-12:30 Oral Session 6: Issues in lexicon construction and Machine Translation
12:00–12:30 Unsupervised Construction of a Lexicon and a Repository of Variation Patterns for Arabic Modal Multiword Expressions Rania Al-Sabbagh, Roxana Girju and Jana diesner
12:30–14:00 Lunch
14:00-14:30 Oral Session 6: Issues in lexicon construction and Machine Translation (continued)
14:00–14:30 Issues in Translating Verb-Particle Constructions from German to English Nina Schottmüller and Joakim Nivre
14:30–15:30 Invited Talk 3: Ekaterina Shutova - Title: "Statistical modelling of metaphor"
15:30–15:45 Closing remarks
Program Committee
Iñaki Alegria, University of the Basque Country (Spain) Dimitra Anastasiou, University of Bremen (Germany) Doug Arnold, University of Essex (UK) Eleftherios Avramidis, DFKI GmbH (Germany) Tim Baldwin, University of Melbourne (Australia) Núria Bel, Universitat Pompeu Fabra (Spain) Chris Biemann, Technische Universität Darmstadt (Germany) Francis Bond, Nanyang Technological University (Singapore) Lars Borin, University of Gothenburg (Sweden) António Branco, University of Lisbon (Portugal) Miriam Butt, Universität Konstanz (Germany) Aoife Cahill, ETS (USA) Ken Church, IBM Research (USA) Matthieu Constant, Université Paris-Est Marne-la-Vallée (France) Paul Cook, University of Melbourne (Australia) Béatrice Daille, Nantes University (France) Koenraad De Smedt, University of Bergen (Norway) Gaël Dias, University of Caen Basse-Normandie (France) Gülşen Eryiğit, Istanbul Technical University (Turkey) Tomaž Erjavec, Jožef Stefan Institute (Slovenia) Joaquim Ferreira da Silva, New University of Lisbon (Portugal) Roxana Girju, University of Illinois at Urbana-Champaign (USA) Chikara Hashimoto, National Institute of Information and Communications Technology (Japan) Ulrich Heid, Universität Hildesheim (Germany) Kyo Kageura, University of Tokyo (Japan) Ioannis Korkontzelos, University of Manchester (UK) Brigitte Krenn, Austrian Research Institute for Artificial Intelligence (Austria) Cvetana Krstev, University of Belgrade (Serbia) Marie-Catherine de Marneffe, The Ohio State University (USA) Takuya Matsuzaki, National Institute of Informatics (Japan) Preslav Nakov, Qatar Computing Research Institute (Qatar) Malvina Nissim, University of Bologna (Italy) Joakim Nivre, Uppsala University (Sweden) Diarmuid Ó Séaghdha, University of Cambridge (UK) Jan Odijk, University of Utrecht (The Netherlands) Yannick Parmentier, Université d'Orléans (France) Pavel Pecina, Charles University in Prague (Czech Republic) Scott Piao, Lancaster University (UK) Adam Przepiórkowski, Institute of Computer Science, Polish Academy of Sciences (Poland) Victoria Rosén, University of Bergen (Norway) Carlos Ramisch, Aix-Marseille University (France) Manfred Sailer, Goethe University Frankfurt am Main (Germany) Magali Sanches Duran, University of São Paulo (Brazil) Violeta Seretan, University of Geneva (Switzerland) Ekaterina Shutova, University of California, Berkeley (USA) Jan Šnajder, University of Zagreb (Croatia) Pavel Straňák, Charles University in Prague (Czech Republic) Sara Stymne, Uppsala University (Sweden) Stan Szpakowicz, University of Ottawa (Canada) Beata Trawinski, Institut für Deutsche Sprache (IDS), Mannheim (Germany) Yulia Tsvetkov, Carnegie Mellon University (USA) Yuancheng Tu, Microsoft (USA) Ruben Urizar, University of the Basque Country (Spain) Gertjan van Noord, University of Groningen (The Netherlands) Aline Villavicencio, Federal University of Rio Grande do Sul (Brazil) Veronika Vincze, Hungarian Academy of Sciences (Hungary) Martin Volk, University of Zurich (Switzerland) Tom Wasow, Stanford University (USA) Shuly Wintner, University of Haifa (Israel) Dekai Wu, The Hong Kong University of Science & Technology (Hong Kong)
Workshop Organizers Valia Kordoni (Humboldt Universität zu Berlin, Germany) Markus Egg (Humboldt Universität zu Berlin, Germany) Agata Savary, special track organizer (Université François Rabelais Tours, France) Eric Wehrli, special track organizer (Université de Genève, Switzerland) Stefan Evert (Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany)
Contact For any inquiries regarding the workshop please send an email to mweworkshop.eacl2014 at gmail.com