EACL 2009

Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics

30 March ­ 3 April 2009 Megaron Athens International Conference Centre Athens, Greece

Production and Manufacturing by TEHNOGRAFIA DIGITAL PRESS, 7 Ektoros Street, 152 35 Vrilissia, Athens, Greece Platinum Sponsors:

Gold Sponsors:

Silver Sponsors:

Bronze Sponsors:

Supporters:

Bag Supporter:

c 2009 The Association for Computational Linguistics Order copies of this and other ACL proceedings from: Association for Computational Linguistics (ACL) 209 N. Eighth Street Stroudsburg, PA 18360 USA Tel: +1-570-476-8006 Fax: +1-570-476-0860 acl@aclweb.org

ii

Preface: General Chair
Welcome to the 12th Conference of the European Chapter of the Association for Computational Linguistics--EACL 2009. This is the largest ever EACL in terms of the number of papers being presented. There are also ten workshops, four tutorials, a demos session and a student research workshop. I hope that you will enjoy this full and diverse programme. This is the first time that an EACL conference that is not held jointly with ACL has had a General Chair. Having a General Chair is the EACL Board's strategy for ensuring continuity in the organisation of their conferences, now that the triennial EACLs are not synchronised with the biennial changes to personnel on the board. My job as General Chair is to liaise between the organising team and the EACL board, and to offer advice when needed. What an easy job it has been! And that is thanks wholly to the fantastic people who have done all the hard work to make this conference happen. I could not have asked for a better team of people. I would like to thank them all. First, the Programme Committee, chaired by Claire Gardent and Joakim Nivre, attracted a record number of submissions. Thanks to their efforts, we have our largest ever main programme. I am very excited by the sheer breadth of topics and methodologies that are to be presented at this conference. It was a total pleasure to deal with the Programme Chairs ­ Joakim especially often offered me valuable advice on many matters concerning the conference, particularly electronic publication. I can't thank Claire and Joakim enough for all they have done to make this EACL conference a success. I would also like to thank Ann Copestake and Franciska de Jong for agreeing to be the keynote speakers. For the first time, the three ACL conferences coordinated the call for workshop proposals. This gave proposers more flexibility in choosing the location for their workshops. The Workshop Chairs for EACL, Miriam Butt and Steve Clark, coordinated with the workshop chairs for NAACL 2009 and ACL 2009 in reviewing all the workshop proposals. This coordination inevitably makes the task more complex. But the whole process ran very smoothly thanks to their careful and diligent work. I'm very grateful to Steve and Miriam for putting together a very exciting and broad workshop programme for EACL. As is traditional, the student research workshop was organised by the student members of the EACL board ­ Vera Demberg, Yanjun Ma and Nils Reiter. Their job is very demanding; they essentially do everything that programme chairs do, only on a slightly smaller scale. They issued the call, organised a fantastic team of reviewers, assigned papers, coordinated and mediated among reviewers, and finally constructed a schedule consisting of four parallel sessions. They did a brilliant job, and with very little help from me. I owe them a huge debt of thanks. The Tutorial Chairs, Emiel Krahmer and David Weir, could be viewed as victims of their own success! Their efforts to attract tutorial proposals produced a record number of submissions; many more excellent proposals than we could accommodate. We have a very strong programme of four tutorials, and I thank the tutorials team for all their careful and thoughtful work. The task of producing both the electronic and hard copy versions of the conference materials has become extremely complex as the conference has increased in size and diversity. The Publications Chairs, Kemal Oflazer and David Schlangen, somehow make it look easy. Thanks to them and Ion Androutsopoulous, the member of the local organising team who liaised with them, we have all the materials delivered on time and in good order. In these depressing economic times, being a Sponsorship Chair is a challenging task, and for the most part a thankless one. This year, for the first time, the three ACL conferences coordinated applications for sponsorship funds. This allowed companies to sponsor ACL, EACL and NAACL in one package. The Sponsorship Chairs are Josef van Genabith and Philipp Koehn for Europe, Hitoshi Isahara and Kim-Teng Lua for Asia, and Nicolas Nikolov for the US. They issued hundreds of applications to companies all

iii

over the world. While sponsorship income is generally lower than in previous years, I am convinced it would be much lower still, if they had not coordinated their efforts this way, and done such a thorough job of asking everyone and anyone for money. I am really grateful to them. We received a record number of submissions to the demos session, making it necessary for the Demos Chair, J¨ rn Kreutel, to recruit additional reviewers at the last minute. I would like to thank him for o overcoming the reviewing problems so quickly and efficiently, and thank also the team of reviewers for doing such a great job. I would also like to thank Priscilla Rassmussen, who has been a very valuable source of information and advice for me over the last 3 years. I have really appreciated her thoughtful suggestions and her help in keeping me informed about ACL protocols. Last, but definitely not least, the local organising team have been nothing short of spectacular. The Local Chair, Vangelis Karkaletsis, has been working for over two years on an overwhelming number of tasks, ranging from finding the conference venue and liaising with its management, through dealing with special dietary requirements, to acquiring local sponsorship. Vangelis has always been accessible to me, to other members of the organising team, and to delegates. I simply don't know where he gets his energy from, but I wish he could bottle it and sell it. Thanks to him, my job as General Chair has been stress free. I owe him a huge debt. Vangelis has been backed by the Co-chairs Stelios Piperidis and Ion Androutsopoulos. Stelios also has boundless energy and his effortless charm makes him very effective at persuading people to part with money (what an asset!). I am particularly impressed with the achievements of Vangelis and Stelios in attracting local sponsors, achieving their sponsorship targets even in the current financial climate. Ion's responsibilities have centred largely on publications and publicity, in particular liaising with the Publications Chairs. In spite of the sheer complexity of the task, thanks to him everything has run smoothly. Ion's careful attention to detail has been a really valuable asset on many fronts. The Local Chair and Co-chairs have been backed up by a strong team of local organisers; there are just too many of them for me to thank individually here. I have always felt that the conference has been in excellent hands; every member of the local organising team is highly competent, unflappable, and professional to the last. I thank them all. We have also received unwavering support from the academic institutions to which our three local cochairs belong: NCSR Demokritos, Athens University of Economics and Business, and the Institute for Language and Speech Processing. These institutions have subsidised expenses directly that are associated with secretarial work and the travel costs of invited speakers and tutors. They have also provided all sorts of support that are essentially hidden costs, in administration, publicity, web design and maintenance, and much much more. This conference simply wouldn't happen without this help, and I thank them all. I very much hope that EACL 2009 offers you the opportunity to engage in stimulating debate with fellow researchers in computational linguisitcs. And I hope to see you again next year in Uppsala at the jointly held meeting with ACL. Alex Lascarides General Chair March 2009

iv

Preface: Program Chairs
We are delighted to present you with this volume containing the papers accepted for presentation at the 12th Conference of the European Chapter of the Association for Computational Linguistics, held in Athens, Greece, from March 30th till April 3rd 2009. EACL 2009 received yet another record-breaking number of submissions, with 360 valid submissions against 264 for EACL 2006 and 181 for EACL 2003. Thanks to the new policy adopted by EACL regarding modes of presentation, we were nonetheless able to accept 100 papers (of which 2 were later withdrawn), achieving a healthy acceptance rate of 28% against only 20% in 2006 and 27% in 2003. Indeed, in 2009, the EACL conference will renew its format by having the main conference papers presented either as regular talks or as posters, with posters getting both a ten-minute quick-fire presentation in a thematic session and a one-hour discussion period in a traditional poster session. EACL 2009 will thus feature 41 posters and 57 talks, all with equal status in terms of quality and appearance in the proceedings. Not only does this move towards a balanced mix of traditional talks, quick-fire presentations and poster sessions allow us to maintain a reasonable acceptance rate, we also believe that it will increase interaction between researchers and contribute to a more lively scientific exchange. The increased number of submissions naturally comes with an increased reviewing load and we are greatly indebted to the 11 area chairs who recruited 449 reviewers and managed the reviewing process in their areas. Each paper submission was reviewed by three reviewers, who were furthermore encouraged to discuss any divergences they might have, and the papers in each area were ranked by the area chair. The final selection was made by the program co-chairs after an independent check of all reviews and discussions with the area chairs. In addition to the main conference program, EACL 2009 will feature the now traditional Student Research Workshop, 10 workshops, 4 tutorials and a demo session with 18 presentations. We are also fortunate to have Ann Copestake, University of Cambridge, and Franciska de Jong, University of Twente, as invited speakers. Ann Copestake will speak about "Slacker semantics: why superficiality, dependency and avoidance of commitment can be the right way to go" and Franciska de Jong will discuss "NLP and the humanities: the revival of an old liaison." An event of this size is a highly collaborative effort and we are grateful to all those who helped us construct the main conference program: the authors for submitting their research results; the reviewers for delivering their reviews and discussing them whenever there was some disagreement; and the area chairs for managing the review process in their area. Thanks are due to the START people, Rich Gerber and Paolo Gai, for responding to questions quickly and for modifying START whenever this was needed, and to the local organizing committee chairs, Vangelis Karkaletsis, Ion Androutsopoulos and Stelios Piperidis, for their patient cooperation with us over many organisational issues. We are also grateful to the Student Research Workshop chairs, Vera Demberg, Yanjun Ma and Nils Reiter, and to the NAACL HLT program chairs, Michael Collins, Lucy Vanderwende, Doug Oard and Shri Narayanan, for smooth collaboration in the handling of double submissions. Finally, we are indebted to the General Chair, Alex Lascarides, for her lively guidance and support throughout the whole process, and to the two Publication Chairs, David Schlangen and Kemal Oflazer, for putting together the conference proceedings. Wishing you a very enjoyable time at EACL 2009! Claire Gardent and Joakim Nivre EACL 2009 Program Chairs

v

EACL 2009 Organizers

General Chair: Alex Lascarides, University of Edinburgh (UK) Programme Chairs: Claire Gardent, CNRS/LORIA Nancy (France) Joakim Nivre, Uppsala University and V¨ xj¨ University (Sweden) a o Invited Speakers: Ann Copestake, University of Cambridge (UK) Franciska de Jong, University of Twente (The Netherlands) Workshop Chairs: Miriam Butt, University of Konstanz (Germany) Stephen Clark, University of Cambridge (UK) Tutorial Chairs: Emiel Krahmer, University of Tilburg (The Netherlands) David Weir, University of Sussex (UK) Student Research Workshop Chairs: Vera Demberg, University of Edinburgh (UK) Yanjun Ma, Dublin City University (Ireland) Nils Reiter, Heidelberg University (Germany) Demos Chair: J¨ rn Kreutel, Semantic Edge (Germany) o Publications Chairs: Kemal Oflazer, Sabanci University (Turkey) David Schlangen, University of Potsdam (Germany)

vii

Sponsorship Chairs: Josef van Genabith, Dublin City University (Ireland) Philipp Koehn, University of Edinburgh (UK) Hitoshi Isihara, NICT (Japan) Kim-Teng Lua, National University of Singapore (Singapore) Nicolas Nicolov, JD Powers (USA) Vangelis Karkaletsis, NCSR Demokritos (Greece) Stelios Piperidis, Institute for Language and Speech Processing (Greece) Local Chairs: Vangelis Karkaletsis, NCSR Demokritos (Greece) Ion Androutsopoulos, Athens University of Economics and Business (Greece) Stelios Piperidis, Institute for Language and Speech Processing (Greece) Local Organizing Team: Dimitrios Galanis, Athens University of Economics and Business (Greece) Maria Gavrilidou, Institute for Language and Speech Processing (Greece) Georgios Gianakopoulos, NCSR Demokritos (Greece) Elias Iosif, NCSR Demokritos (Greece) Pythagoras Karampiperis, NCSR Demokritos (Greece) Stasinos Konstantopoulos, NCSR Demokritos (Greece) Gerasimos Lampouras, Athens University of Economics and Business (Greece) Prodromos Malakasiotis, Athens University of Economics and Business (Greece) Stella Markantonatou, Institute for Language and Speech Processing (Greece) Evgenia Pantouvaki, NCSR Demokritos (Greece) Anastasios Patrikakos, Institute for Language and Speech Processing (Greece) Georgios Petasis, NCSR Demokritos (Greece) Kostas Stamatakis, NCSR Demokritos (Greece) Georgios Tsatsaronis, NCSR Demokritos and Athens University of Economics and Business (Greece)

viii

EACL 2009 Program Committee

Program Chairs: Claire Gardent, CNRS/LORIA Nancy (France) Joakim Nivre, Uppsala University and V¨ xj¨ University (Sweden) a o Area Chairs: Anja Belz, University of Brighton (UK) Sabine Buchholz, Toshiba Research Europe (UK) Chris Callison-Burch, Johns Hopkins University (USA) Philipp Cimiano, Delft University of Technology (The Netherlands) Maarten de Rijke, University of Amsterdam (The Netherlands) Anna Korhonen, University of Cambridge (UK) Kimmo Koskenniemi, University of Helsinki (Finland) Bernardo Magnini, FBK-irst (Italy) Stephan Oepen, University of Oslo (Norway) Richard Power, The Open University (UK) Giuseppe Riccardi, University of Trento (Italy) Program Committee Members: Anne Abeill´ , Omri Abend, Meni Adler, Eneko Agirre, David Ahn, Lars Ahrenberg, Amparo e Albalate, Mikhail Alexandrov, Enrique Alfonseca, Gianni Amati, Saba Amsalu, Mohammed Attia, Nathalie Aussenac-Gilles Tim Baldwin. Krisztian Balog, Srinivas Bangalore, Marco Baroni, Roberto Basili, John Bateman, Frederic Bechet, Abdelmajid Ben Hamadou, Emily Bender, Anton Benz, Jonathan Berant, Sabine Bergler, Raffaella Bernardi, Delphine Bernhard, Nicola Bertoldi, Rahul Bhagat, Ergun Bicici, ¸ Eckhard Bick, Tam´ s Bir´ , Philippe Blache, Xavier Blanco, Phil Blunsom, Rens Bod, Bernd a o Bohnet, Dan Bohus, Ondrej Bojar, Gemma Boleda, Francis Bond, Johan Bos, Mohand Boughanem, Gosse Bouma, Antonio Branco, Thorsten Brants, Chris Brew, Christopher Brewster, Ted Briscoe, Paul Buitelaar, Harry Bunt, Aljoscha Burchardt, Donna Byron Aoife Cahill, Zoraida Callejas, Nicoletta Calzolari, Sandra Carberry, Marine Carpuat, Xavier Carreras, John Carroll, Francisco Casacuberta, Mauro Cettolo, Nouha Cha^ bane, Yee Seng Chan, a Ming-Wei Chang, Eugene Charniak, Ciprian Chelba, Stanley Chen, Colin Cherry, David Chiang, Massimiliano Ciaramita, Stephen Clark, James Clarke, Trevor Cohn, Michael Connor, Bonaventura Coppola, Stephen Cox, Nick Craswell, Montserrat Cuadros, James Curran, James Cussens Walter Daelemans, Ido Dagan, Robert Dale, Hercules Dalianis, Geraldine Damnati, Noa Danon, Hal Daum´ III, Dmitry Davidov, Guy De Pauw, Thierry Declerck, Rodolfo Delmonte, David e DeVault, Giuseppe Di Fabbrizio, Mona Diab, Anne Diekema, Christine Doran, Qing Dou, Markus Dreyer, Amit Dubey, Chris Dyer, Helge Dyvik Markus Egg, Andreas Eisele, Elisabet Engdahl, Katrin Erk, Maxine Eskenazi, Cristina Espa~ a, n Roger Evans, Stefan Evert Afsaneh Fazly, Marcello Federico, Christiane Fellbaum, Raquel Fern´ ndez, Olivier Ferret, Dan a Flickinger, George Foster, Jennifer Foster, Mary Ellen Foster, Anette Frank, Alex Fraser, Fumiyo Fukumoto

ix

Aldo Gangemi, Nikesh Garera, Albert Gatt, Dale Gerdemann, Ulrich Germann, Dafydd Gibbon, Daniel Gildea, Jesus Gimenez, Kevin Gimpel, Jonathan Ginzburg, Roxana Girju, Alfio Gliozzo, John Goldsmith, Julio Gonzalo, Allen Gorin, Genevieve Gorrell, Brigitte Grau, Mark Greenwood, Gregory Grefenstette, David Griol, Claire Grover, Iryna Gurevych Ben Hachey, Lamia Hadrich Belguith, Udo Hahn, Dilek Hakkani-T¨ r, Keith Hall, Greg u Hanneman, Sanda Harabagiu, Donna Harman, Sasa Hasan, Kenneth Heafield, Ulrich Heid, James Henderson, John Henderson, Iris Hendrickx, Gerhard Heyer, Andrew Hickl, Djoerd Hiemstra, Erhard Hinrichs, Graeme Hirst, Jerry Hobbs, Julia Hockenmaier, Deirdre Hogan, Mark Hopkins, Veronique Hoste, Arvi Hurskainen, Rebecca Hwa Nancy Ide, Diana Inkpen, Neil Ireson, Amy Isard, Alexei Ivanov Guillaume Jacquet, Jerom Janssen, Sittichai Jiampojamarn, Valentin Jijkoun, Richard Johansson, Sofie Johansson Kokkinakis, Rie Johnson (formerly, Ando), Michael Johnston, Kristiina Jokinen, Doug Jones, Gareth Jones, Aravind Joshi Heiki Kaalep, Laura Kallmeyer, Min-Yen Kan, Viggo Kann, Damianos Karakos, Jussi Karlgren, Fred Karlsson, Lauri Karttunen, Martin Kay, Simon Keizer, Jaana Kekalainen, Frank Keller, Bernd Kiefer, Adam Kilgarriff, Tracy King, Kevin Knight, Alistair Knott, Philipp Koehn, Dimitrios Kokkinakis, Alexander Koller, Greg Kondrak, Valia Kordoni, Zornitsa Kozareva, Bob Krovetz, Yuval Krymolowski, Taku Kudo, Sandra K¨ bler, Peter K¨ hnlein, Marco Kuhlmann, u u Jonas Kuhn, Roland Kuhn, Shankar Kumar, Jeff Kuo, Oren Kurland, Sadao Kurohashi, Olivia Kwong Tore Langholm, Guy Lapalme, Mirella Lapata, Alberto Lavelli, Alon Lavie, Gary Lee, Fabrice Lefevre, Jochen Leidner, Oliver Lemon, Alessandro Lenci, Piroska Lendvai, Ian Lewin, Zhifei Li, Frank Liberato, Jimmy Lin, Krister Lind´ n, Kenneth Litkowski, Peter Ljungl¨ f, Birte e o Loenneker-Rodman, Adam Lopez Nitin Madnani, Thomas Mandl, Inderjeet Mani, Daniel Marcu, Katja Markert, Llu´s M` rquez i a Villodre, Erwin Marsi, Colin Matheson, Lambert Mathias, Yuji Matsumoto, Takuya Matsuzak, Arne Mauseri, Diana McCarthy, David McClosky, Ryan McDonald, Michael McTear, Ben Medlock, Paola Merlo, Slim Mesfar, Donald Metzler, Jeffrey Micher, Rada Mihalcea, Maria Milosavljevic, Wolfgang Minker, Yusuke Miyao, Sien Moens, Dan Moldovan, Simonetta Montemagni, Christof Monz, Bob Moore, Roser Morante, Alessandro Moschitti, Smaranda Muresan, Stefan M¨ ller u Vivi Nastase, Sven Naumann, Roberto Navigli, Mark-Jan Nederhof, Ani Nenkova, G¨ nter u Neumann, Hermann Ney, Hwee Tou Ng, Patrik Nguyen, Rodney Nielsen, Sergei Nirenburg, Malvina Nissim, Tadashi Nomoto ´ e Diarmuid O S´ aghdha, Franz-Josef Och, Kemal Oflazer, Alessandro Oltramari, Constantin Orasan, Csaba Oravecz, Miles Osborne, Rainer Osswald, Lilja Øvrelid Sebastian Pad´ , Tim Paek, Patrick Pantel, Rebecca Passonneau, Catherine Pelachaud, Anselmo o Pe~ as, Gerald Penn, Marco Pennacchiotti, Wim Peters, Kay Peterson, Emanuele Pianta, Paul n Piwek, Massimo Poesio, Thierry Poibeau, Alexandros Potamianos, Judita Preiss, Laurent Prevot, James Pustejovsky Lizhen Qu, Silvia Quarteroni, Chris Quirk Jan Raab, Aarne Ranta, Ari Rappoport, Christian Raymond, Gisela Redeker, Ehud Reiter, Martin Reynaert, Sebastian Riedel, Verena Rieser, Stefan Riezler, German Rigau, Michael Riley, Brian Roark, Laurent Romary, Barbara Rosario, Mike Rosner, Dan Roth, Salim Roukos Kenji Sagae, Patrick Saint-Dizier, Emilio Sanchis, Diana Santos, Giorgio Satta, Jacques Savoy, David Schlangen, Judith Schlesinger, Helmut Schmid, Sabine Schulte im Walde, Donia Scott,

x

Fr´ d´ rique Segond, Satoshi Sekine, Libin Shen, Wade Shen, Eyal Shnarch, B¨ rkur e e o Sigurbj¨ rnsson, Max Silberztein, Rui Sousa Silva, Khalil Sima'an, Michel Simard, Kiril Simov, o Vivek Srikumar, Inguna Skadina, David Smith, Noah Smith, Rion Snow, Radu Soricut, Caroline Sporleder, Manfred Stede, Mark Steedman, Josef Steinberger, Svetlana Stenchikova, Amanda Stent, Mark Stevenson, Suzanne Stevenson, Matthew Stone, Carlo Strapparava, Michael Strube, Eiichiro Sumita, Mihai Surdeanu Maite Taboada, David Talbot, Thora Tenbrink, Simone Teufel, J¨ rg Tiedemann, Christoph o Tillmann, Ivan Titov, Takenobu Tokunaga, Kristina Toutanova, Trond Trosterud, Theodora Tsikrika, Dan Tufis, Juho Tupakka, Gokhan Tur, Peter Turney ¸ Nicola Ueffing Antal van den Bosch, Lelka van der Sluis, Marieke van Erp, Josef van Genabith, Hans van Halteren, Gertjan van Noord, Menno van Zaanen, Keith Vander Linden, Lucy Vanderwende, Tam´ s V´ radi, Sebastian Varges, Tony Veale, Paola Velardi, Karin Verspoor, Jose Luis Vicedo, a a Barbora Vidova-Hladka, Simona Vietri, Laure Vieu, Aline Villavicencio, Eric Villemonte de la Clergerie, Dusko Vitas, Andreas Vlachos, Carl Vogel, Clare Voss, Piek Vossen, Atro Voutilainen Qin Iris Wang, Nigel Ward, Taro Watanabe, Andy Way, Gabe Webster, Richard Wicentowski, Sandra Williams, Jason Williams, Shuly Wintner, Yuk Wah Wong, Jeremy Wright, Dekai Wu Fei Xia Alexander Yeh, Anssi Yli-Jyr¨ , Kai Yu, Deniz Yuret a Fabio Massimo Zanzotto, Sina Zarrieß, Richard Zens, Torsten Zesch, Yi Zhang, Imed Zitouni, Ingrid Zukerman

xi

Table of Contents
Invited Talk: Slacker Semantics: Why Superficiality, Dependency and Avoidance of Commitment can be the Right Way to Go Ann Copestake . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 Invited Talk: NLP and the Humanities: The Revival of an Old Liaison Francisca de Jong . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 On the Use of Comparable Corpora to Improve SMT performance Sadaf Abdul-Rauf and Holger Schwenk . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 Contextual Phrase-Level Polarity Analysis Using Lexical Affect Scoring and Syntactic N-Grams Apoorv Agarwal, Fadi Biadsy and Kathleen Mckeown . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 Personalizing PageRank for Word Sense Disambiguation Eneko Agirre and Aitor Soroa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 Supervised Domain Adaption for WSD Eneko Agirre and Oier Lopez de Lacalle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 Clique-Based Clustering for Improving Named Entity Recognition Systems Julien Ah-Pine and Guillaume Jacquet . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 Correcting Automatic Translations through Collaborations between MT and Monolingual Target-Language Users Joshua Albrecht, Rebecca Hwa and G. Elisabeta Marai . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60 Incremental Parsing with Parallel Multiple Context-Free Grammars Krasimir Angelov . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69 Data-Driven Semantic Analysis for Multilingual WSD and Lexical Selection in Translation Marianna Apidianaki . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77 Syntactic Phrase Reordering for English-to-Arabic Statistical Machine Translation Ibrahim Badr, Rabih Zbib and James Glass . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 86 Incremental Parsing Models for Dialog Task Structure Srinivas Bangalore and Amanda Stent . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94 Bayesian Word Sense Induction Samuel Brody and Mirella Lapata . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 103 Human Evaluation of a German Surface Realisation Ranker Aoife Cahill and Martin Forst . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 112 Large-Coverage Root Lexicon Extraction for Hindi Cohan Sujay Carlos, Monojit Choudhury and Sandipan Dandapat . . . . . . . . . . . . . . . . . . . . . . . . . . 121 Lexical Morphology in Machine Translation: A Feasibility Study Bruno Cartoni . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 130 Predicting the Fluency of Text with Shallow Structural Features: Case Studies of Machine Translation and Human-Written Text Jieun Chae and Ani Nenkova . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 139

xiii

EM Works for Pronoun Anaphora Resolution Eugene Charniak and Micha Elsner . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 148 Web Augmentation of Language Models for Continuous Speech Recognition of SMS Text Messages Mathias Creutz, Sami Virpioja and Anna Kovaleva . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 157 An Alignment Algorithm Using Belief Propagation and a Structure-Based Distortion Model Fabien Cromier` s and Sadao Kurohashi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 166 e Translation and Extension of Concepts Across Languages Dmitry Davidov and Ari Rappoport . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 175 Learning to Interpret Utterances Using Dialogue History David DeVault and Matthew Stone . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 184 Correcting Dependency Annotation Errors Markus Dickinson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 193 Re-Ranking Models for Spoken Language Understanding Marco Dinarelli, Alessandro Moschitti and Giuseppe Riccardi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 202 Inference Rules and their Application to Recognizing Textual Entailment Georgiana Dinu and Rui Wang . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 211 Semi-Supervised Semantic Role Labeling Hagen F¨ rstenau and Mirella Lapata . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 220 u Cognitively Motivated Features for Readability Assessment Lijun Feng, No´ mie Elhadad and Matt Huenerfauth . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 229 e Effects of Word Confusion Networks on Voice Search Junlan Feng and Srinivas Bangalore . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 238 Company-Oriented Extractive Summarization of Financial News Katja Filippova, Mihai Surdeanu, Massimiliano Ciaramita and Hugo Zaragoza. . . . . . . . . . . . . . .246 Reconstructing False Start Errors in Spontaneous Speech Text Erin Fitzgerald, Keith Hall and Frederick Jelinek . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 255 TBL-Improved Non-Deterministic Segmentation and POS Tagging for a Chinese Parser Martin Forst and Ji Fang . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 264 Who is "You"? Combining Linguistic and Gaze Features to Resolve Second-Person References in Dialogue Matthew Frampton, Raquel Fern´ ndez, Patrick Ehlen, Mario Christoudias, Trevor Darrell and Stana ley Peters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 273 Rich Bitext Projection Features for Parse Reranking Alexander Fraser, Renjing Wang and Hinrich Sch¨ tze . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 282 u Parsing Mildly Non-Projective Dependency Structures Carlos G´ mez-Rodr´guez, David Weir and John Carroll . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 291 o i Structural, Transitive and Latent Models for Biographic Fact Extraction Nikesh Garera and David Yarowsky . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 300

xiv

Semitic Morphological Analysis and Generation Using Finite State Transducers with Feature Structures Michael Gasser . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 309 Cube Summing, Approximate Inference with Non-Local Features, and Dynamic Programming without Semirings Kevin Gimpel and Noah A. Smith . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 318 Enhancing Unlexicalized Parsing Performance Using a Wide Coverage Lexicon, Fuzzy Tag-Set Mapping, and EM-HMM-Based Lexical Probabilities Yoav Goldberg, Reut Tsarfaty, Meni Adler and Michael Elhadad . . . . . . . . . . . . . . . . . . . . . . . . . . . 327 Person Identification from Text and Speech Genre Samples Jade Goldstein-Stewart, Ransom Winder and Roberta Sabin . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 336 End-to-End Evaluation in Simultaneous Translation Olivier Hamon, Christian F¨ gen, Djamel Mostefa, Victoria Arranz, Muntsin Kolss, Alex Waibel u and Khalid Choukri . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 345 Learning-Based Named Entity Recognition for Morphologically-Rich, Resource-Scarce Languages Kazi Saidul Hasan, Md. Altaf ur Rahman and Vincent Ng . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 354 Weakly Supervised Part-of-Speech Tagging for Morphologically-Rich, Resource-Scarce Languages Kazi Saidul Hasan and Vincent Ng . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 363 Improving Mid-Range Re-Ordering Using Templates of Factors Hieu Hoang and Philipp Koehn . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 372 Rule Filtering by Pattern for Efficient Hierarchical Translation Gonzalo Iglesias, Adri` de Gispert, Eduardo R. Banga and William Byrne . . . . . . . . . . . . . . . . . . . 380 a An Empirical Study on Class-Based Word Sense Disambiguation Rub´ n Izquierdo, Armando Su´ rez and German Rigau . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 389 e a Generating a Non-English Subjectivity Lexicon: Relations That Matter Valentin Jijkoun and Katja Hofmann . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 398 Parsing Coordinations Sandra K¨ bler, Erhard Hinrichs, Wolfgang Maier and Eva Klett . . . . . . . . . . . . . . . . . . . . . . . . . . . . 406 u Automatic Single-Document Key Fact Extraction from Newswire Articles Itamar Kastner and Christof Monz . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 415 N-Gram-Based Statistical Machine Translation versus Syntax Augmented Machine Translation: Comparison and System Combination Maxim Khalilov and Jos´ A. R. Fonollosa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 424 e Lightly Supervised Transliteration for Machine Translation Amit Kirschenbaum and Shuly Wintner . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 433 Optimization in Coreference Resolution is not Needed: A Nearly-Optimal Algorithm with Intensional Constraints ´ Manfred Klenner and Etienne Ailloud . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 442 A Logic of Semantic Representations for Shallow Parsing Alexander Koller and Alex Lascarides . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 451

xv

Dependency Trees and the Strong Generative Capacity of CCG Alexander Koller and Marco Kuhlmann . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 460 Lattice Parsing to Integrate Speech Recognition and Rule-Based Machine Translation Selcuk K¨ pr¨ and Adnan Yazici . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 469 ¸ o u Treebank Grammar Techniques for Non-Projective Dependency Parsing Marco Kuhlmann and Giorgio Satta . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 478 Improvements in Analogical Learning: Application to Translating Multi-Terms of the Medical Domain Philippe Langlais, Francois Yvon and Pierre Zweigenbaum . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 487 ¸ Language-Independent Bilingual Terminology Extraction from a Multilingual Parallel Corpus Els Lefever, Lieve Macken and Veronique Hoste . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 496 User Simulations for Context-Sensitive Speech Recognition in Spoken Dialogue Systems Oliver Lemon and Ioannis Konstas . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 505 Sentiment Summarization: Evaluating and Learning User Preferences Kevin Lerman, Sasha Blair-Goldensohn and Ryan McDonald . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 514 Correcting a POS-Tagged Corpus Using Three Complementary Methods Hrafn Loftsson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 523 Translation as Weighted Deduction Adam Lopez . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 532 Performance Confidence Estimation for Automatic Summarization Annie Louis and Ani Nenkova . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 541 Bilingually Motivated Domain-Adapted Word Segmentation for Statistical Machine Translation Yanjun Ma and Andy Way . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 549 Evaluating the Inferential Utility of Lexical-Semantic Resources Shachar Mirkin, Ido Dagan and Eyal Shnarch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 558 Text-to-Text Semantic Similarity for Automatic Short Answer Grading Michael Mohler and Rada Mihalcea . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 567 Syntactic and Semantic Kernels for Short Text Pair Categorization Alessandro Moschitti . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 576 Discovering Global Patterns in Linguistic Networks through Spectral Analysis: A Case Study of the Consonant Inventories Animesh Mukherjee, Monojit Choudhury and Ravi Kannan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 585 Using Cycles and Quasi-Cycles to Disambiguate Dictionary Glosses Roberto Navigli . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 594 Deterministic Shift-Reduce Parsing for Unification-Based Grammars by Using Default Unification Takashi Ninomiya, Takuya Matsuzaki, Nobuyuki Shimizu and Hiroshi Nakagawa . . . . . . . . . . . . 603 Analysing Wikipedia and Gold-Standard Corpora for NER Training Joel Nothman, Tara Murphy and James R. Curran . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 612

xvi

Using Lexical and Relational Similarity to Classify Semantic Relations ´ e Diarmuid O S´ aghdha and Ann Copestake . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 621 Empirical Evaluations of Animacy Annotation Lilja Øvrelid . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 630 Outclassing Wikipedia in Open-Domain Information Extraction: Weakly-Supervised Acquisition of Attributes over Conceptual Hierarchies Marius Pasca . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 639 ¸ Predicting Strong Associations on the Basis of Corpus Data Yves Peirsman and Dirk Geeraerts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 648 Measuring Frame Relatedness Marco Pennacchiotti and Michael Wirth . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 657 Flexible Answer Typing with Discriminative Preference Ranking Christopher Pinchak, Dekang Lin and Davood Rafiei . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 666 Semi-Supervised Polarity Lexicon Induction Delip Rao and Deepak Ravichandran . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 675 Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems Verena Rieser and Oliver Lemon . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 683 Tagging Urdu Text with Parts of Speech: A Tagger Comparison Hassan Sajjad and Helmut Schmid . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 692 Unsupervised Methods for Head Assignments Federico Sangati and Willem Zuidema . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 701 A General, Abstract Model of Incremental Dialogue Processing David Schlangen and Gabriel Skantze . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 710 Word Lattices for Multi-Source Translation Josh Schroeder, Trevor Cohn and Philipp Koehn . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 719 Frequency Matters: Pitch Accents and Information Status Katrin Schweitzer, Michael Walsh, Bernd M¨ bius, Arndt Riester, Antje Schweitzer and Hinrich o Sch¨ tze . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 728 u Using Non-Lexical Features to Identify Effective Indexing Terms for Biomedical Illustrations Matthew Simpson, Dina Demner-Fushman, Charles Sneiderman, Sameer K. Antani and George R. Thoma . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 737 Incremental Dialogue Processing in a Micro-Domain Gabriel Skantze and David Schlangen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 745 Unsupervised Recognition of Literal and Non-Literal Use of Idiomatic Expressions Caroline Sporleder and Linlin Li . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 754 Semi-Supervised Training for the Averaged Perceptron POS Tagger Drahom´ra "johanka" Spoustov´ , Jan Haji , Jan Raab and Miroslav Spousta . . . . . . . . . . . . . . . . . 763 i a c Sequential Labeling with Latent Variables: An Exact Inference Algorithm and its Efficient Approximation Xu Sun and Jun'ichi Tsujii . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 772

xvii

Text Summarization Model Based on Maximum Coverage Problem and its Variant Hiroya Takamura and Manabu Okumura . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 781 Fast Full Parsing by Linear-Chain Conditional Random Fields Yoshimasa Tsuruoka, Jun'ichi Tsujii and Sophia Ananiadou . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 790 MINT: A Method for Effective and Scalable Mining of Named Entity Transliterations from Large Comparable Corpora Raghavendra Udupa, K Saravanan, A Kumaran and Jagadeesh Jagarlamudi . . . . . . . . . . . . . . . . . . 799 Deriving Generalized Knowledge from Corpora Using WordNet Abstraction Benjamin Van Durme, Phillip Michalak and Lenhart Schubert . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 808 Learning Efficient Parsing Gertjan van Noord . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 817 A Robust and Extensible Exemplar-Based Model of Thematic Fit Bram Vandekerckhove, Dominiek Sandra and Walter Daelemans . . . . . . . . . . . . . . . . . . . . . . . . . . . 826 Growing Finely-Discriminating Taxonomies from Seeds of Varying Quality and Size Tony Veale, Guofu Li and Yanfen Hao . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 835 Feature-Based Method for Document Alignment in Comparable News Corpora Thuy Vu, Ai Ti Aw and Min Zhang . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 843 Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument Satisfaction Model Stephen Wan, Mark Dras, Robert Dale and C´ cile Paris . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 852 e Co-Dispersion: A Windowless Approach to Lexical Association Justin Washtell . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 861 Language ID in the Context of Harvesting Language Data off the Web Fei Xia, William Lewis and Hoifung Poon . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 870 Character-Level Dependencies in Chinese: Usefulness and Learning Hai Zhao . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 879

xviii