International Workshop on Spoken Language Translation

2-3 December, 2010
Paris, France

 

Program

 

Published proceedings

 

Thursday, December 2nd, 2010

 

Welcome remarks: Joseph Mariani (LIMSI-CNRS & IMMI, France)

 

Invited talk: Is machine translation ripe for EU translators? Josep Bonet (DG Translation of the European Commisssion) [abstract]

 

Main findings of the evaluation campaign: Michael Paul, Marcello Federico and Sebastian Stüker (FBK-irst, Italy; NICT, Japan; Karlsruhe Institute of Technology, Germany) … pp.3-27

 

TALK task: The ITI-UPV machine translation system for IWSLT 2010: Guillem Gascó, Vicent Alabau, Jesús-Andrés-Ferrer, Jesús González-Rubio, Martha-Alicia Rocha, Germán Sanchis-Trilles, Francisco Casacuberta, Jorge González, and Joan-Andreu Sánchez (Universidad Politécnica de Valencia, Spain) - presentation

DIALOG task: The MSRA machine translation system for IWSLT 2010: Chi-Ho Li, Nan Duan, Yinggong Zhao, Shujie Liu, Lei Cui, Mei-yuh Hwang, Amittai Axelrod, Jianfeng Gao, Yaodong Zhang, and Li Deng (Microsoft Research Asia, Natural Language Computing, China) - presentation

BTEC task: The MIT-LL/AFRL IWSLT-2010 system: Wade Shen, Timothy Anderson, Raymond Slyh, and A.Ryan Aminzadeh (MIT Lincoln Laboratory, USA) - presentation

 

Invited talk: Hierarchical phrase-based translation with weighted finite state transducers: William Byrne (Cambridge University, UK) [abstract]

 

If I only had a parser: poor man’s syntax for hierarchical machine translation: David Vilar, Daniel Stein, Stephan Peitz, and Hermann Ney (RWTH Aachen University, Germany)…pp.345-352

Dynamic distortion in a discriminative reordering model for statistical machine translation: Sirvan Yahyaei and Christoph Monz (University of London, UK; University of Amsterdam, The Netherlands)…pp.353-360

Factor templates for factored machine translation models: Yvette Graham and Josef van Genabith (Dublin City University, Ireland)…pp.275-282

 

Poster session I

 

LIMSI @ IWSLT 2010: Alexandre Allauzen, Josep M.Crego, İlknur Durgar El-Kahlout, Le Hai-Son, Guillaume Wisniewski, and François Yvon (LIMSI-CNRS, France)…pp.105-112

LIUM’s statistical machine translation system for IWSLT 2010: Anthony Rousseau, Loïc Barrault, Paul Deléglise, and Yannick Estève (University of Le Mans, LIUM, France)…pp.113-117

FBK @ IWSLT 2010: Arianna Bisazza, Ioannis Klasinas, Mauro Cettolo, and Marcello Federico (Fondazione Bruno Kessler, Ricerca Scientifica e Tecnologica, Italy)…pp.53-58

The TÜBİTAK-UEKAE statistical machine translation system for IWSLT 2010: Coskun Mermer, Hamza Kaya, and Mehmet Ugur Dogan (TUBITAK-UEKAE, Turkey) …pp.183-188

ITI-UPV machine translation system for IWSLT 2010: Guillem Gascó, Vicent Alabau, Jesús-Andrés-Ferrer, Jesús González-Rubio, Martha-Alicia Rocha, Germán Sanchis-Trilles, Francisco Casacuberta, Jorge González, and Joan-Andreu Sánchez (Universidad Politécnica de Valencia, Instituto Universitario Mixto de Tecnología Informática, Spain)…pp.85-92

The KIT translation system for IWSLT 2010: Jan Niehues, Mohammed Mediani, Teresa Herrmann, Michael Heck, Christian Herff, and Alex Waibel (Karlsruhe Institute of Technology, Germany)…pp.93-98

NTT statistical MT system for IWSLT 2010: Katsuhito Sudoh, Kevin Duh, and Hajime Tsukada (NTT Communication Science Labs, Japan)…pp.147-152

LIG statistical machine translation systems for IWSLT 2010: Laurent Besacier, Haitem Afli, Do Thi Ngoc Diep, Hervé Blanchon, and Marion Potet (University J.Fourier, GETALP, LIG, France)…pp.99-104

The MIT-LL/AFRL IWSLT-2010 MT system: Wade Shen, Timothy Anderson, Raymond Slyh, and A.Ryan Aminzadeh (MIT Lincoln Laboratory, USA)…pp.127-134

The MSRA machine translation system for IWSLT 2010: Chi-Ho Li, Nan Duan, Yinggong Zhao, Shujie Liu, Lei Cui, Mei-yuh Hwang, Amittai Axelrod, Jianfeng Gao, Yaodong Zhang, and Li Deng (Microsoft Research Asia, Natural Language Computing, China)…pp.135-138

Hybrid approach for MT based on cross-language information retrieval: Christophe Servan and Nasredine Semmar (CEA Laboratoire d’Intégration des Systèmes et des Technologies, France) – paper not available

A Bayesian model of bilingual segmentation for transliteration: Andrew Finch and Eiichiro Sumita (NICT, Japan)…pp.259-266

Comparing intrinsic and extrinsic evaluation of MT output in a dialogue system: Anne H.Schneider, Ielka van der Sluis, and Saturnino Luz (Trinity College, Dublin, Ireland)…pp.329-336

Faster cube pruning: Andrea Gesmundo and James Henderson (University of Geneva, Switzerland)…pp.267-274

Real-time spoken language identification and recognition for speech-to-speech translation: Daniel Chung Yong Lim, Ian Lane and Alex Waibel (Carnegie Mellon University, USA; DSO National Laboratories, Singapore)…pp.307-312

Sign language machine translation overkill: Daniel Stein, Christoph Schmidt, and Hermann Ney (RWTH Aachen University, Germany)…pp.337-344

The pay-offs of preprocessing for German-English statistical machine translation: Ilknur Durgar El-Kahlout and Francois Yvon (Univ. Paris-Sud and LIMSI-CNRS, France)…pp.251-258

Towards a general and extensible phrase-extraction algorithm: Wang Ling, Tiago Luís, João Graça, Luísa Coheur and Isabel Trancoso (L2F Spoken Systems Lab, INESC-ID Portugal)...pp.313-320

Analysis of translation model adaptation in statistical machine translation: Kevin Duh, Katsuhito Sudoh, and Hajime Tsukada (NTT Communication Science Laboratories, Japan)…pp.243-250

ITU-T standardization on network-based speech-to-speech translation: Chiori Hori and Satoshi Nakamura (NICT, Japan) – paper not available

 

Friday, December 3rd, 2010

 

Invited talk: Resources for adding semantics to machine translation: Jan Hajič (Charles University in Prague) [abstract]

 

Oral Session II

 

Mining parallel fragments from comparable texts: Mauro Cettolo, Marcello Federico, and Nicola Bertoldi (Fondazione Bruno Kessler, Italy)…pp.227-234

Multi-pivot translation by system combination: Gregor Leusch, Aurélien Max, Josep Maria Crego, and Hermann Ney (RWTH Aachen University, Germany; LIMSI-CNRS, France; Univ. Paris Sud, France) …pp.299-306

An algorithm for cross-lingual sense-clustering tested in a MT evaluation setting: Marianna Apidianaki and Yifan He (Alpage, INRIA & Université Paris 7, France; Dublin City University, Ireland)…pp.219-226

 

Invited talk: The Quaero program: multilingual and multimedia technologies: Jean-Luc Gauvain (LIMSI/CNRS, Orsay, France) [abstract]

 

A combination of hierarchical systems with forced alignments from phrase-based systems: Carmen Heger, Joern Wuebker, David Vilar, & Hermann Ney (RWTH Aachen University, Germany)…pp.291-297

CCG augmented hierarchical phrase-based machine translation: Hala Almaghout, Jie Jiang, and Andy Way (Dublin City University)…pp.211-218

Modelling pronominal anaphora in statistical machine translation: Christian Hardmeier and Marcello Federico (Fondazione Bruno Kessler, Italy)…pp.283-289

 

Poster Session II

 

AppTek’s APT machine translation system for IWSLT 2010: Evgeny Matusov and Selçuk Köprü (Apptek, Inc., Turkey)… pp.29-36

The ICT statistical machine translation system for IWSLT 2010: Hao Xiong, Jun Xie, Hui Yu, Kai Liu, Wei Luo, Haitao Mi, Yang Liu, Yajuan Lü, and Qun Liu (Chinese Academy of Sciences, Institute of Computing Technology, China)…pp.73-79

The DCU machine translation systems for IWSLT 2010: Hala Almaghout, Jie Jiang, and Andy Way (Dublin City University, School of Computing, Ireland)… pp.37-44

I2R’s machine translation system for IWSLT 2010: Xiangyu Duan, Rafael Banchs, Jun Lang, Deyi Xiong, Aiti Aw, Min Zhang, and Haizhou Li (Institute for Infocomm Research, Singapore)…pp.67-72

The INESC-ID machine translation system for the IWSLT 2010: Wang Ling, Tiago Luís, João Graça, Luísa Coheur and Isabel Trancoso (Instituto de Engenharia de Sistemas e Computasores Investigacao e Desenvolvimento, Portugal)…pp.81-84

The MIRACL Arabic-English statistical machine translation system for IWSLT 2010: Ines Turki Khemakhem, Salma Jamoussi, and Abdelmajid Ben Hamadou (MIRACL Laboratory, Tunisia)…pp.119-125

The NICT translation  system for IWSLT 2010: Chooi-Ling Goh, Taro Watanabe, Michael Paul, Andrew Finch, and Eiichiro Sumita  (National Institute of Information and Communications Technology, Japan)…pp.139-146

The POSTECH’s statistical machine translation system for the IWSLT 2010: Hwidong Na and Jong-Hyeok Lee (Pohang University of Science and Technology, Korea)…pp.153-156

The QMUL system description for IWSLT 2010: Sirvan Yahyaei and Christof Monz (University of London, United Kingdom)…pp.157-162

The RWTH Aachen machine translation system for IWSLT 2010: Saab Mansour, Stephan Peitz, David Vilar, Joern Wuebker, and Hermann Ney (RWTH Aachen University, Germany)…pp.163-168

Tel Aviv University’s system description for IWSLT 2010: Kfir Bar and Nachum Dershowitz (Tel Aviv University, Israel)…pp.169-174

Statistical pattern-based MT with statistical French-English MT: Jin’ichi Murakami, Takuya Nishimura and Masao Tokuhisa (Tottori University, Japan)…pp.175-182

N-gram-based machine translation enhanced with neural networks: Francisco Zamora-Martinez, Maria Jose Castro-Bleda, and Holger Schwenk (Universidad CEU-Cardenal Herrera Politecnica de Valencia, Spain)… pp.45-52

UPC-BMIC-VDU system description for the IWSLT 2010: testing several collocation segmentations in a phrase-based SMT system: Carlos Henríquez, Marta R.Costa-jussà, Vidas Daudaravicius, Rafael E.Banchs, & José B.Mariño (Universitat Politécnica de Catalunya, Spain)…pp.189-195

ILLC-UvA machine translation system for the IWSLT 2010 evaluation: Maxim Khalilov and Khalil Sima’an (University Amsterdam, The Netherlands)…pp.197-203

The UvA system description for IWSLT 2010: Spyros Martzoukos and Christof Monz (University Amsterdam, The Netherlands)…pp.205-208

The GREYC/LLACAN machine translation systems for the IWSLT 2010 campaign: Julien Gosme, Wigdan Mekki, Fathi Debili, Yves Lepage and Nadine Lucas (University of Caen Basse-Normandie, GREYC, France)…pp.59-65

Morphology-to-syntax alignment for factored phrase-based SMT: Kemal Oflazer and Reyyan Yeniterzi (Carnegie Mellon University, Qatar Campus, Qatar) – paper not available

Improved Vietnamese-French parallel corpus mining using English language: Do Thi Ngoc Diep, Laurent Besacier, and Eric Castelli (LIG Laboratory, France; MICA Center, Vietnam)…pp.235-242

MorphTagger: HMM-based Arabic segmentation for statistical machine translation: Saab Mansour (RWTH Aachen University, Germany)…pp.321-327