Proceedings of the 3rd Workshop on Noisy User-generated Text
著者: Jake Williams, Agata Savary, Carlos Ramisch, Silvio Cordeiro, Fed- Erico Sangati, Veronika Vincze, Francesco Barbieri, Luis Espinosa-Anke, Miguel Ballesteros, Juan Soler-Company, Horacio Saggion, Horacio Saggion, Wei Ai, Xuan Lu, Xuanzhe Liu, Ning Wang, Gang Huang, Qiaozhu Mei, Sho Aoki, Osamu Uchida, Peng Liu, Wei Chen, Gaoyan Ou, Tengjiao Wang, Dongqing Yang, Kai Lei, Nikola Ljubesic, Darja Fiser, Jean Hannah, Daniel Miller, Jacob Kluver, Loren Thebault-Spieker, Brent Terveen, Hecht, M Saif, Svetlana Mohammad, Parinaz Kiritchenko, Xiaodan Sobhani, Colin Zhu, Cherry, Petra Kralj Novak, Jasmina Smailovic, Borut Sluban, Igor Mozetic, Jedrzej Olejniczak, Bo Pang, Lillian Lee, Jaram Park, Young, Min Baek, Meeyoung Cha, Jaram Park, Vladimir Barash, Clay Fink, Meeyoung Cha, Antonio Reyes, Paolo Rosso, Tony Veale, Antonio Reyes, Paolo Rosso, Tony Veale, Tamara Small, Thomas Smith, Marianna Obrist, Peter Wright, Emilio Sulis, Delia Iraz, Hernndez Faras, Paolo Rosso, Viviana Patti, Giancarlo Ruffo, Oren Tsur, Dmitry Davidov, Ari Rappoport, Oriol Vinyals, Lukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, Geoffrey Hinton, Po-Ya Angela Wang, Jianshu Weng, Bu-Sung Lee, Hadi Amiri, Hal Daum, Iii, Hadi Amiri, Hal Daum, Iii, Aime Backiel, Bart Baesens, Gerda Claeskens, Mohit Bansal, Kevin Gimpel, Karen Livescu, Yoshua Bengio, Rjean Ducharme, Pascal Vincent, Christian Jauvin, Ronan Collobert, Jason Weston, Lon Bottou, Michael Karlen, Koray Kavukcuoglu, Pavel Kuksa, George Dahl, Dong Yu, Li Deng, Alex Acero, James Foulds, Shachi Kumar, Lise Getoor, Kuzman Ganchev, Jennifer Gillenwater, Ben Taskar, Ge Hinton, De Rumelhart, Williams, Geoffrey Hinton, Li Deng, Dong Yu, George Dahl, Abdel-Rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara Sainath, Sorami Hisamoto, Kevin Duh, Yuji Matsumoto, Alexander Hogenboom, Paul Van Iterson, Bas Heerschop, Flavius Frasincar, Uzay Kaymak, Fei Huang, Arun Ahuja, Doug Downey, Yi Yang, Yuhong Guo, Alexander Yates, Lifeng Jia, Clement Yu, Weiyi Meng, Abbas Keramati, Hajar Ghaneei, Seyed Mohammad, Mirmohammadi, Alex Krizhevsky, Ilya Sutskever, Geoffrey Hinton, Ruiqi Li, Peng Wang, Zonghai Chen, Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, Jeff Dean, Marvin Minsky, Anh Nguyen, Jason Yosinski, Jeff Clune, Jeffrey Pennington, Richard Socher, Christopher Manning, Geoffrey David E Rumelhart, Ronald Hinton, Williams, Tim Salimans, P Diederik, Kingma, Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher Manning, Andrew Ng, Christopher Potts, Ilya Sutskever, Oriol Vinyals, Quoc V Le, Joseph Turian, Lev Ratinov, Yoshua Bengio, Timothy Baldwin, Marie-Catherine De Marneffe, Bo Han, Young-Bum Kim, Alan Ritter, Wei Xu, Michael Beiwenger, Sabine Bartsch, Stefan Evert, Kay-Michael Wrzner, Marcel Bollmann, Cristina Bosco, Fabio Tamburini, Andrea Bolioli, Alessandro Mazzei, Leo Breiman, Jacob Eisenstein, Jennifer Foster, zlem Cetinoglu, Joachim Wagner, Joseph Le Roux, Joakim Nivre, Deirdre Hogan, Josef Van Genabith, Kevin Gimpel, Nathan Schneider, Brendan O' Connor, Dipanjan Das, Daniel Mills, Jacob Eisenstein, Michael Heilman, Dani Yogatama, Jeffrey Flanigan, Noah Smith, Rob Van Der Goot, Gertjan Van Noord, Nicholas Andrews, Jason Eisner, Mark Dredze, Anietie Andy, Mugizi Rwebangira, Satoshi Sekine, Anietie Andy, Satoshi Sekine, Mugizi Rwebangira, Mark Dredze, Mark Dredze, Nicholas Andrews, Jay Deyoung, Stephen Guo, Ming-Wei Chang, Emre Kiciman, Xiaohua Liu, Yitong Li, Haocheng Wu, Ming Zhou, Furu Wei, Yi Lu, J Michael, Mark Paul, Dredze, Lars Backstrom, Jure Leskovec, Adrian Benton, Raman Arora, Mark Dredze, V Quoc, Tomas Le, Mikolov, David Liben, - Nowell, Jon Kleinberg, Shuchuan Lo, Chingching Lin, Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, Jeff Dean, Radim ehek, Petr Sojka, Xiaojun Wan, Yang Yu, Xinjie Zhou, Faiyaz Al Zamal, Wendy Liu, Derek Ruths, Ugo Jalal S Alowibdi, Philip Buy, Yu, Shlomo Argamon, Moshe Koppel, James Pennebaker, Jonathan Schler, Shane Bergsma, Paul Mcnamee, Mossaab Bagdouri, Clayton Fink, Theresa Wilson, John Blitzer, Mark Dredze, Fernando Pereira, John Blitzer, Ryan Mcdonald, Fernando Pereira, Lin Su, Lisa Blodgett, Brendan O' Green, Connor, Baden Hughes, Timothy Baldwin, Steven Bird, Jeremy Nicholson, Andrew Mackinlay, Aaron Jaech, George Mulcaire, Shobhit Hathi, Mari Ostendorf, Noah Smith, Ben King, Steven Abney, Tom Kocmi, Ondej Bojar, Marco Lui, T Baldwin, Marco Lui, Timothy Baldwin, Marco Lui, Paul Cook, Barbara Plank, Jennifer Williams, Charlie Dagli, Yi Yang, Jacob Eisenstein, Amr Ahmed, Liangjie Hong, Alexander Smola, Zhiyuan Cheng, James Caverlee, Kyumin Lee, Lianhua Chi, Hui Kwan, Nebula Lim, Christopher Alam, Butler, Jacob Eisenstein, O' Brendan, Noah Connor, Eric Smith, Xing, Aoife Cahill, Nitin Madnani, Joel Tetreault, Diane Napolitano, Courtney Napoles, Keisuke Sakaguchi, Matt Post, Joel Tetreault, Tou Hwee, Ng, Mei Siew, Ted Wu, Christian Briscoe, Raymond Hadiwinoto, Christopher Susanto, Bryant, Alla Rozovskaya, Dan Roth, Alla Rozovskaya, Mark Sammons, Dan Roth, Zheng Yuan, Ted Briscoe, Omar Benjelloun, Hector Garcia-Molina, David Menestrina, Qi Su, Steven Whang, Jennifer Widom, Hamish Cunningham, Artur Dubrawski, Kyle Miller, Matthew Barnes, Benedikt Boecking, Emily Kennedy, Johannes Frnkranz, Peter Flach, Fabian Pedregosa, Gal Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, douard Duchesnay, Pedro Szekely, Craig Knoblock, Jason Slepicka, Andrew Philpot, Amandeep Singh, Chengye Yin, Dipsy Kapoor, Prem Natarajan, Daniel Marcu, Kevin Knight, David Stallard, Subessware Karunamoorthy, Rajagopal Bojanapalli, Steven Minton, Brian Amanatullah, Todd Hughes, Mike Tamayo, David Flynt, Rachel Artiss, Shih-Fu Chang, Tao Chen, Gerald Hiebel, Lidia Ferreira, Sriharsha Veeramachaneni, Ravi Kumar, Kondadadi, Ahmet Arslan, Aiti Aw, Min Zhang, Juan Xiao, Jian Su, Richard Beaufort, Sophie Roekhaut, Louise-Amlie Cougnon, Cdrick Fairon, Wilson Woodrow, Iben Bledsoe, Browning, Vladimir Cherkassky, Nikolaos Vassilas, Monojit Choudhury, Rahul Saraf, Vijit Jain, Animesh Mukherjee, Sudeshna Sarkar, Anupam Basu, W Kenneth, William Church, Gale, Eleanor Clark, Kenji Araki, Paul Cook, Suzanne Stevenson, Fred Damerau, Jean Rahman, Duval, Walis Abdukerim, Janbaz, Kenneth Heafield, Taishi Ikeda, Hiroyuki Shindo, Yuji Matsumoto, Catherine Kobus, Graldine Franc ois Yvon, Damnati, Karen Kukich, Eric Mays, Fred Damerau, Robert Mercer, Rada Mihalcea, Vivi Nastase, L Deana, Yang Pennell, Liu, M Edward, Allen Riseman, Hanson, Richard Sproat, Alan Black, Stanley Chen, Shankar Kumar, Mari Ostendorf, Christopher Richards, J Emmanuel, David Yannakoudakis, Fawthrop, Manish Agarwal, Prashanth Mannem, Jonathan Berant, Andrew Chou, Roy Frostig, Percy Liang, R Samuel, Gabor Bowman, Christopher Angeli, Christopher Potts, Manning, Leo Breiman, Peter Clark, Peter Clark, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Oyvind Tafjord, Peter Turney, Daniel Khashabi, Peter Clark, Philip Harrison, Niranjan Balasubramanian, Rui Correia, Jorge Baptista, Nuno Mamede, Isabel Trancoso, Maxine Eskenazi, Michael Heilman, Noah Smith, Karl Moritz Hermann, Tom Koisk, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, Phil Blunsom, Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Peter Clark, Oren Etzioni, Dan Roth, Tushar Khot, Niranjan Balasubramanian, Eric Gribkoff, Ashish Sabharwal, Peter Clark, Oren Etzioni, Yang Li, Peter Clark, Michael Mausam, Robert Schmitz, Stephen Bart, Oren Soderland, Etzioni, Ruslan Mitkov, Le An Ha, Ruslan Mitkov, An Le, Andrea Ha, Luz Varga, Rello, Jack Mostow, Hyeju Jang, Takeshi Onishi, Hai Wang, Mohit Bansal, Kevin Gimpel, David Mcallester, Andreas Papasalouros, Konstantinos Kanaris, Konstantinos Kotis, Jeffrey Pennington, Richard Socher, Christopher Manning, Juan Pino, Maxine Esknazi, Juan Pino, Michael Heilman, Maxine Eskenazi, P Rajpurkar, J Zhang, K Lopyrev, P Liang, Keisuke Sakaguchi, Yuki Arase, Mamoru Komachi, Eiichiro Sumita, Fumiaki Sugaya, Seiichi Yamamoto, Yi Yang, Scott Wen-Tau Yih, Chris Meek, Torsten Zesch, Oren Melamud, Aiti Aw, Min Zhang, Juan Xiao, Jian Su, Steven Bird, Edward Loper, Ewan Klein, Jacob Eisenstein, Bo Han, Timothy Baldwin, Bo Han, Paul Cook, Timothy Baldwin, Adam Kilgarriff, Joseph Rosenzweig, Arne Khn, Florian Stegen, Timo Baumann, Stuart Moore, Sabine Buchholz, Anna Korhonen, Barbara Plank, Vivek Kumar, Rangarajan Sridhar, Brian Roark, Richard Sproat, Richard Sproat, Alan Black, Stanley Chen, Shankar Kumar, Mari Ostendorf, Christopher Richards, Amr Ahmed, Liangjie Hong, Alexander Smola, Zhiyuan Cheng, James Caverlee, Kyumin Lee, Lianhua Chi, Hui Kwan, Nebula Lim, Christopher Alam, Butler, Jacob Eisenstein, O' Brendan, Noah Connor, Eric Smith, Xing, Bo Han, Paul Cook, Timothy Baldwin, Bo Han, Paul Cook, Timothy Baldwin, Liangjie Hong, Amr Ahmed, Siva Gurumurthy, Alexander Smola, Kostas Tsioutsiouliklis, Y Andrew, Ng, Reid Priedhorsky, Aron Culotta, Sara Y Del Valle, Afshin Rahimi, Trevor Cohn, Timothy Baldwin, Alan Ritter, Sam Clark, Mausam, Oren Etzioni, Stephen Roller, Michael Speriosu, Sarat Rallapalli, Benjamin Wing, Jason Baldridge, Bahar Salehi, Anders Sgaard, Hirotugu Akaike, Sugato Basu, Arindam Banerjee, Raymond Mooney, Chih-Chung Chang, Chih-Jen Lin, D Jinho, Andrew Choi, Mccallum, Christopher Clark, Santosh Divvala, Afef Kacem, Abdel Belad, Mohamed Ben, Ahmed, Asima Shah Khusro, Irfan Latif, Ullah, Michael Kohlhase, Ioan Sucan, Kristina Lerman, Craig Knoblock, Steven Minton, Xiaoyan Lin, Liangcai Gao, Zhi Tang, Xiaofan Lin, Xuan Hu, Ying Liu, Kun Bai, Prasenjit Mitra, C Giles, Tou Hwee, Chung Ng, Jessica Lim, Teng Li, Koo, L O'gorman, David Pinto, Andrew Mccallum, Xing Wei, W Croft, Anik Simon, Jean-Christophe Pret, A Peter Johnson, Masakazu Suzuki, Fumikazu Tamari, Ryoji Fukuda, Seiichi Uchida, Toshihiro Kanahori, Suppawong Tuarob, Sumit Bhatia, Prasenjit Mitra, C Giles, Stefano Baccianella, Andrea Esuli, Fabrizio Sebastiani, Preeti Bhargava, Nemanja Spasojevic, Guoning Hu, Prantik Bhattacharyya, Nemanja Spasojevic, Andrea Esuli, Fabrizio Sebastiani, Mihai Christopher D Manning, John Surdeanu, Jenny Bauer, Steven Finkel, David Bethard, Mcclosky, Dat Ba Nguyen, Johannes Hoffart, Martin Theobald, Gerhard Weikum, Jeffrey Pennington, Richard Socher, Christopher Manning, Adithya Rao, Nemanja Spasojevic, Zhisheng Li, Trevor Dsouza, Alan Ritter, Mausam Clark, Sam, Oren Etzioni, Alan Ritter, Oren Mausam, Sam Etzioni, Clark, Nemanja Spasojevic, Preeti Bhargava, Guoning Hu, Nemanja Spasojevic, Prantik Bhattacharyya, Adithya Rao, Nemanja Spasojevic, Adithya Rao, Gustavo Aguilar, Suraj Maharjan, Adrian Pastor, Lpez Monroy, Thamar Solorio, Isabelle Augenstein, Leon Derczynski, Kalina Bontcheva, Timothy Baldwin, Young-Bum Kim, Marie, Catherine Marneffe, Alan Ritter, Bo Han, Wei Xu, Steven Bird, Kalina Bontcheva, Ian Roberts, Leon Derczynski, Dominic Rout, Jason Pc Chiu, Eric Nichols, Leon Derczynski, Kalina Bontcheva, Leon Derczynski, Kalina Bontcheva, Ian Roberts, Leon Derczynski, Diana Maynard, Giuseppe Rizzo, Marieke Van Erp, Genevieve Gorrell, Raphal Troncy, Johann Petrak, Kalina Bontcheva, Leon Derczynski, Alan Ritter, Sam Clark, Kalina Bontcheva, Johannes Hoffart, Yasemin Altun, Gerhard Weikum, Eduard Hovy, Mitchell Marcus, Martha Palmer, Lance Ramshaw, Ralph Weischedel, Patrick Jansson, Shuhua Liu, Yuzhe Jin, Emre Kcman, Kuansan Wang, Ricky Loynd, Saul A Kripke, Bill Lin, Frank Xu, Zhiyi Luo, Kenny Zhu, Xiaohua Liu, Shaodian Zhang, Furu Wei, Ming Zhou, Marco Lui, Timothy Baldwin, Mihai Christopher D Manning, John Surdeanu, Jenny Bauer, Steven Finkel, David Bethard, Mc-Closky, Marcelo Montemurro, O' Brendan, Michel Connor, David Krieger, Ahn, Marten Postma, Filip Ilievski, Piek Vossen, Marieke Van Erp, Marta Recasens, Marie-Catherine De Marneffe, Christopher Potts, Alan Ritter, Sam Clark, Mausam, Oren Etzioni, Giuseppe Rizzo, Bianca Pereira, Andrea Varga, Marieke Van Erp, Amparo Cano Basave, Giuseppe Rizzo, Marieke Van Erp, Julien Plu, Raphal Troncy, Erik Tjong, Kim Sang, Utpal Kumar, Sikdar, Bjrn Gambck, Benjamin Strauss, Bethany Toma, Alan Ritter, Marie-Catherine De Marneffe, Wei Xu, Erik Tjong, Kim Sang, Fien De, Meulder, Pablo Marieke Van Erp, Heiko Mendes, Filip Paulheim, Julien Ilievski, Giuseppe Plu, Joerg Rizzo, Waitelonis, Mark Pius Von Dniken, Cieliebak, Jake Williams, Giovanni Santia, Eiji Aramaki, Yasuhide Miura, Masatsugu Tonoike, Tomoko Ohkuma, Hiroshi Mashuichi, Kazuhiko Ohe, Mohammed Attia, Suraj Maharjan, Younes Samih, Laura Kallmeyer, Thamar Solorio, Michele Banko, Michael Cafarella, Stephen Soderland, Matt Broadhead, Oren Etzioni, Joachim Bingel, Anders Sgaard, Hsinchun Chen, Wingyan Chung, Jennifer Xu, Gang Wang, Yi Qin, Michael Chau, Ronan Collobert, Jason Weston, Leon Derczynski, Eric Nichols, Marieke Van Erp, Nut Limsopatham, Frderic Godin, Baptist Vandersmissen, Wesley De Neve, Rik Van De Walle, Chenliang Li, Jianshu Weng, Qi He, Yuxia Yao, Anwitaman Datta, Aixin Sun, Bu-Sung Lee, Nut Limsopatham, Nigel Collier, Gang Luo, Xiaojiang Huang, Chin-Yew Lin, Zaiqing Nie, John Suraj Maharjan, Manuel Arevalo, Fabio Montes, Thamar Gonzlez, Solorio, Hctor Martnez, Alonso, Barbara Plank, Shubhanshu Mishra, Jana Diesner, Olutobi Owoputi, O' Brendan, Chris Connor, Kevin Dyer, Nathan Gimpel, Noah Schneider, Smith, Lev Ratinov, Dan Roth, Alan Ritter, Sam Clark, Mausam, Oren Etzioni, Anders Sgaard, Yoav Goldberg, Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov, D Blei, A Ng, M Jordan, D Blei, Benjamin Strauss, Bethany Toma, Alan Ritter, Marie Catherine De Marneffe, Wei Xu, Baldwin Timothy, Young-Bum Kim, Marie Catherine De Marneffe, Alan Ritter, Bo Han, Wei Xu, Chiu Jason, P, Eric Nichols, Diana Maynard, Giuseppe Rizzo, Marieke Van Erp, Genevieve Gorrell, Johann Raphae L Troncy, Kalina Petrak, Bontcheva, Derczynski Leon, Eric Nichols, Marieke Van Erp, Godin Frederic, Baptist Vandersmissen, Wesley De Neve, Rik Vande, Walle, Hasan Sadid, A, Yuan Ling, Joey Liu, Oladimeji Farri, M Hoffman, D Blei, F Bach, Huang Zhiheng, Wei Xu, Kai Yu ; John, Andrew Mccallum, Fernando Pereira, Ioffe Sergey, Szregedy Christian, Mccallum Andrew, Wei Li, Mikolov Tomas, Kai Chen, Greg Corrado, Jeffrey Dean, Mikolov Tomas, Ilya Sutskever, Kai Chen, Greg Corrado, Jeffrey Dean, Pennington Jeffrey, Richard Socher, Christopher Manning, Vosoughi Soroush, Prashanth Vijayaraghavan, Deb Roy, Zhang Xiang, Junbo Zhao, Yann Lecun, Isabelle Augenstein, Leon Derczynski, Kalina Bontcheva, Timothy Baldwin, Young-Bum Kim, Marie, Catherine Marneffe, Alan Ritter, Bo Han, Wei Xu, Leon Derczynski, Diana Maynard, Giuseppe Rizzo, Marieke Van Erp, Genevieve Gorrell, Raphal Troncy, Johann Petrak, Kalina Bontcheva, Kevin Gimpel, Nathan Schneider, Brendan O' Connor, Dipanjan Das, Daniel Mills, Jacob Eisenstein, Michael Heilman, Dani Yogatama, Jeffrey Flanigan, Noah Smith, Xavier Glorot, Yoshua Bengio, Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Rafal Jzefowicz, Wojciech Zaremba, Ilya Sutskever, John Lafferty, Andrew Mccallum, Fernando Pereira, Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer, Xuezhe Ma, Eduard Hovy, Andrew Mccallum, Wei Li, Olutobi Owoputi, O' Brendan, Chris Connor, Kevin Dyer, Nathan Gimpel, Noah Schneider, Smith, Jeffrey Pennington, Richard Socher, Christopher Manning, Boliang Zhang, Hongzhao Huang, Xiaoman Pan, Sujian Li, Chin-Yew Lin, Heng Ji, Kevin Knight, Zhen Wen, Yizhou Sun, Jiawei Han, Blent Yener, Ronan Collobert, Jason Weston, Lon Bottou, Michael Karlen, Koray Kavukcuoglu, Pavel Kuksa, Leon Derczynski, Eric Nichols, Marieke Van Erp, Nut Limsopatham, Xavier Glorot, Yoshua Bengio, Sepp Hochreiter, Jrgen Schmidhuber, Vinod Nair, Geoffrey Hinton, Damien Sileo, Camille Pradel, Philippe Muller, Tim Van De Cruys, Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov, Benjamin Strauss, Bethany Toma, Alan Ritter, Marie-Catherine De Marneffe, Wei Xu, Charles Sutton, Andrew Mccallum, Erik Tjong, Kim Sang, Fien De, Meulder, Isabelle Augenstein, Leon Derczynski, Kalina Bontcheva, Johan Bos, Valerio Basile, Kilian Evang, Noortje Venhuizen, Johannes Bjerva, Leon Derczynski, Diana Maynard, Giuseppe Rizzo, Marieke Van Erp, Genevieve Gorrell, Raphal Troncy, Johann Petrak, Kalina Bontcheva, Zhenfei Ju, Jian Wang, Fei Zhu, Giridhar Kumaran, James Allan, John Lafferty, Andrew Mccallum, Fernando Pereira, Gang Luo, Xiaojiang Huang, Chin-Yew Lin, Zaiqing Nie, Andrew Mccallum, Wei Li, Joel Nothman, James Curran, Tara Murphy, Joel Nothman, Nicky Ringland, Will Radford, Tara Murphy, James Curran, S Piantadosi, H Tily, E Gibson, Alan Ritter, Sam Clark, Mausam, Oren Etzioni, Burr Settles, Claude Shannon, Benjamin Strauss, Bethany Toma, Alan Ritter, Marie-Catherine De Marneffe, Wei Xu, Erik Tjong, Kim Sang, Fien De, Meulder, N Konstantinos, Andreas Vavliakis, Pericles Symeonidis, Mitkas, Jake Ryland Williams, Eric Clark, James Bagrow, Christopher Danforth, Peter Sheridan Dodds ; A, Jake Ryland Williams, Paul Lessard, Suma Desu, Eric Clark, James Bagrow, Christopher Danforth, Peter Dodds, Amparo Cano, Daniel Preot iuc-Pietro, Danica Radovanovi, Katrin Weller, Aba-Sah Dadzie, Leon Derczynski, Eric Nichols, Marieke Van Erp, Nut Limsopatham, Sepp Hochreiter, Jrgen Schmidhuber, Hideki Isozaki, Hideto Kazawa, John Lafferty, Andrew Mccallum, Fernando Pereira, Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer, Chenliang Li, Jianshu Weng, Qi He, Yuxia Yao, Anwitaman Datta, Aixin Sun, Bu-Sung Lee, Dong Liu, Jorge Nocedal, Xiaohua Liu, Shaodian Zhang, Furu Wei, Ming Zhou, Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, Jeffrey Dean, Jeffrey Pennington, Richard Socher, Christopher Manning, Daniel Ramage, David Hall, Ramesh Nallapati, Christopher Manning, Alan Ritter, Sam Clark, Mausam, Oren Etzioni, Jrg Waitelonis, Harald Sack - 2017 被引用: 35
This work presents a fine-grained, textchunking algorithm designed for the task of multiword expressions (MWEs) segmentation. As a lexical class, MWEs include a wide variety of idioms, whose automatic identification are a necessity for the handling of colloquial language. This algorithm's core novelty is its use of non-word tokens, i.e., boundaries, in a bottom-up strategy. Leveraging boundaries refines token-level information, forging highlevel performance from relatively basic data. The generality of this model's feature space allows for its application across languages and domains. Experiments spanning 19 different languages exhibit a broadly-applicable, stateof-the-art model. Evaluation against recent shared-task data places text partitioning as the overall, best performing MWE segmentation algorithm, covering all MWE classes and multiple English domains (including usergenerated text). This performance, coupled with a non-combinatorial, fast-running design, produces an ideal combination for implementations at scale, which are facilitated through the release of open-source software.
