Proceedings of the

International Workshop on

Spoken Language Translation

December 6 and 7, 2012

Hong Kong

 

Table of contents

 

Keynote:

Head finalization: translation from SVO to SOV [abstract].

Hideki Isozaki                                                                                                 7

Toward universal network-based speech translation [abstract]

Chai Wutiwiwatchai                                                                                         8

Who can understand your speech better – deep neural network of Gaussian mixture model [abstract]

Dong Yu

                                                                                                            9

Evaluation Campaign

 

Overview of the IWSLT 2012 evaluation campaign.

M.Federico, M.Cettolo, L.Bentivogli, M.Paul, S.Stüker                                    12-33

The NICT ASR system for IWSLT2012

Hitoshi Yamamoto, Youzheng Wu, Chien-Lin Huang, Xugang Lu, Paul R.Dixon, Shigeki Matsuda, Chiori Hori, Hideki Kashioka

                                                                                                                        34-37

The KIT translation systems for IWSLT 2012

Mohammed Mediani, Yuqi Zhang, Thanh-Le Ha, Jan Niehues, Eunach Cho, Teresa Herrmann, Rainer Kärgel, Alexander Waibel

                                                                                                                        38-45

The UEDIN systems for the IWSLT 2012 evaluation

Eva Hasler, Peter Bell, Arnab Ghoshal, Barry Haddow, Philipp Koehn, Fergus McInnes, Steve Renals, Pawel Swietojanski

                                                                                                                        46-53

The NAIST machine translation system for IWSLT2012

Graham Neubig, Kevin Duh, Masaya Ogushi, Takamoto Kano, Tetsuo Kiso, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura

                                                                                                                        54-60

FBK’s machine translation systems for IWSLT 2012’s TED lectures

N.Ruiz, A.Bisazza, R.Cattoni, M.Federico                                                            61-68

The RWTH Aachen speech recognition and machine translation system for IWSLT 2012.

Stephan Peitz, Saab Mansour, Markus Freitag, Minwei Feng, Matthias Huck, Joern Wuebker, Malte Nuhn, Markus Nußbaum-Thom, Hermann Ney

                                                                                                                        69-76

The HIT-LTRC machine translation system for IWSLT 2012

Xiaoning Zhu, Yiming Cui, Conghui Zhu, Tiejun Zhao, Hailong Cao                   77-80

FBK@IWSLT 2012 – ASR track

D.Falavigna, R.Gretter, F.Brugnara, D.Giuliani                                                81-86

The 2012 KIT and KIT-NAIST English ASR systems for the IWSLT evaluation

Christian Saam, Christian Mohr, Kevin Kilgour, Michael Heck, Matthias Sperber, Keigo Kubo, Sebatian Stüker, Sakriani Sakri, Graham Neubig, Tomoki Toda, Satoshi Nakamura, Alex Waibel

                                                                                                                        87-90

The KIT-NAIST (contrastive) English ASR system for IWSLT 2012.

Michael Heck, Keigo Kubo, Matthias Sperber, Sakriani Sakti, Sebastian Stüker, Christian Saam, Kevin Kilgour, Christian Mohr, Graham Neubig, Tomoki Toda, Satoshi Nakamura, Alex Waibel

                                                                                                                        91-95

EBMT system of Kyoto University in OLYMPICS task at IWSLT 2012

Chenhui Chu, Toshiaki Nakazawa, Sadao Kurohashi                                         96-101

The LIG English to French machine translation system for IWSLT 2012

Laurent Besacier, Benjamin Lecouteux, Marwen Azouzi, Luong Ngoc Quang

                                                                                                                        102-108

The MIT-LL/AFRL IWSLT 2012 MT system

Jennifer Drexler, Wade Shen, Tim Anderson, Raymond Slyh, Brian Ore, Eric Hansen Terry Gleason

109-116

Minimum Bayes-risk decoding extended with similar examples: NAIST-NCT at IWSLT 2012

Hiroaki Shimizu, Masao Utiyama, Eiichiro Sumita, Satoshi Nakamura                 117-120

The NICT translation system for IWSLT 2012

Andrew Finch, Ohnmar Htun, Eiichiro Sumita                                                121-125

TED Polish-to-English translation system for the IWSLT 2012

Krzysztof Marasek                                                                                          126-129

Forest-to-string translation using binarized dependency forest for IWSLT 2012 OLYMPICS task

Hwidong Na Jong-Hyeok Lee                                                                          130-135

Romanian to English automatic MT experiments at IWSLT12 – system description paper.

Ştefan Daniel Dumitrescu, Radu Ion, Dan Ştefănescu, Tiberiu Boroş, Dan Tufiş

                                                                                                                        136-143

The TÜBİTAK statistical machine translation system for IWSLT 2012

Coşkun Mermer, Hamza Kaya, İlknur Durgar El-Kahlout, Mehmet Uğur Doğan

                                                                                                                        144-148

Technical Papers

 

Active error detection and resolution for speech-to-speech translation.

Rohit Prasad, Rohit Kumar, Sankaranarayanan Ananthakrishnan, Wei Chen, Sanjika Hewavitharana, Matthew Roy, Frederick Choi, Aaron Challenner, Enoch Kan, Arvid Neelakantan, Prem Natarajan

                                                                                                                        150-157

A method for translation of paralinguistic information

Takatomo Kano, Sakriani Sakti, Shinnosuke Takamichi, Graham Neubig, Tomoki Toda, Satoshi Nakamura

                                                                                                                        158-163

Continuous space language models using restricted Boltzmann machines

Jan Niehues Alex Waibel                                                                                 164-170

Focusing language models for automatic speech recognition

Daniele Falavigna Roberto Gretter                                                                   171-178

Simulating human judgment in machine translation evaluation campaigns

Philipp Koehn                                                                                                  179-184

Semi-supervised transliteration mining from parallel and comparable corpora                       

Walid Aransa, Holger Schwenk, Loic Barrault                                                 185-192

A simple and effective weighted phrase extraction for machine translation adaptation.

Saab Mansour Hermann Ney                                                                           193-200

Applications of data selection via cross-entropy difference for real-world statistical machine translation.

Amittai Axelrod, QingJun Li, William D.Lewis                                               201-208

A universal approach to translating numerical and time expressions

Mei Tu, Yu Zhou Chengqing Zong                                                                  209-216

Evaluation of interactive user corrections for lecture transcription.

Heinrich Kolkhorst, Kevin Kilgour, Sebastian Stüker, Alex Waibel                 217-221

Factored recurrent neural network language model in TED lecture transcription

Youzheng Wu, Hitoshi Yamamoto, Xugang Lu, Shigeki Matsuda, Chiori Hori, Hideki Kashioka

                                                                                                                        222-228

Incremental adaptation using translation information and post-editing analysis

Frédéric Blain, Holger Schwenk, Jean Senellart                                               229-236

Interactive-predictive speech-enabled computer-assisted translation

Shahram Khadivi Zeinab Vakil                                                                        237-243

MDI adaptation for the lazy: avoiding normalization in LM adaptation for lecture translation

Nick Ruiz, Marcello Federico                                                                          244-251

Segmentation and punctuation prediction in speech language translation using a monolingual translation system

Eunah Cho, Jan Niehues, Alex Waibel                                                            252-259

Sequence labeling-based reordering model for phrase-based SMT

Minwei Feng, Jan-Thorsten Peter, Hermann Ney                                             260-267

Sparse lexicalised features and topic adaptation for SMT

Eva Hasler, Barry Haddow, Philipp Koehn                                                      268-275

Spoken language translation using automatically transcribed text in training.

Stephan Peitz, Simon Wiesler, Markus Nußbaum-Thom, Hermann Ney

                                                                                                                        276-283

Towards a better understanding of statistical post-editing

Marion Potet, Laurent Besacier, Hervé Blanchon, Marwen Azouzi                 284-291

Towards contextual adaptation for any-text translation

Li Gong, Aurélien Max, François Yvon                                                           292-299