IWSLT 2015

Proceedings of the

International Workshop on

Spoken Language Translation

December 3-4, 2015

Da Nang, Vietnam

 

Edited by

Marcello Federico

Sebastian Stüker

Jan Niehues

Contents

Keynotes

Improving SMT by model filtering and phrase embedding

Chengqing Zong……xv-xvi

 

Evaluation Campaign

The IWSLT 2015 Evaluation Campaign

                Mauro Cettolo, Jan Niehues, Sebastian Stüker, Luisa Bentivogli, Roldano Cattoni and Marcello Federico……2-14

The RWTH Aachen machine translation system for IWSLT 2015

                Jan-Thorsten Peter, Farzad Toutounchi, Stephan Peitz, Parnia Bahar, Andreas Guta and Hermann Ney…..15-22

The MITLL-AFRL IWSLT 2015 MT system

                Michaeel Kazi, Brian Thompson, Elizabeth Salesky, Timothy Anderson, Grant Erdmann, Eric Hansen, Brian Ore, Katherine Young, Jeremy Gwinnup, Michael Hutt and Christina May…….23-30

The Edinburgh machine translation systems for IWSLT 2015

                Matthias Huck and Alexandra Birch……..31-38

The MLLP ASR systems for IWSLT 2015

                Miguel Ángel Del Agua Teba, Adrià Agusti Martinez Villaronga, Santiago Piqueras Gozalbes, Adrià Giménez Pastor, José Alberto Sanchis Navarro, Jorge Civera Saiz and Alfons Juan Císcar……39-44

The Heidelberg University English-German translation system for IWSLT 2015

                Laura Jehl, PatrickSimianer, Julian HIrschler and Stefan Riezler……45-49

The LIUM ASR and SLT systems for IWSLT 2015

                Mercedes Garcia Martínez, Loïc Barrault, Anthony Rousseau, Paul Deléglise and Yannick Estève……50-54

The UMD machine translation systems at IWSLT 2015

                Amittai Axelrod and Marine Carpuat……55-61

The KIT translation systems for IWSLT 2015

                Thanh-Le Ha, Jan Niehues, Eunah Cho, Mohammed Mediani and Alex Waibel……62-69

The 2015 KIT IWSLT speech-to-text systems for English and German

                Markus Mueller, Tai Son Nguyen, Matthias Sperber, Kevin Kilgour, Sebastian Stuker and Alex Waibel……70-75

Stanford neural machine translation systems for spoken language domains

                Minh-Thang Luong and Christopher Manning……76-79

The English-Vietnamese machine translation system for IWSLT 2015

                Viet Tran Hong, Huyen Vu Thong, Vinh Nguyen Van and Trung Le Tien……80-83

The IOIT English ASR system for IWSLT 2015

                Van Huy Nguyen, Quoc Bao Nguyen, Tat Thang Vu and Chi Mai Luong……84-87

The 12R ASR system for IWSLT 2015

                Huy Dat Tran, Jonathan Dennis and Wen Zheng Ng……88-92

The JAIST-UET-MITI machine translation systems for IWSLT 2015

                Hai-Long Trieu, Thanh-Quyen Dang, Phuong-Thai Nguyen and Le-Minh Nuyen……93-100

PJAIT systems for the IWSLT 2015 evaluation campaign enhanced by comparable corpora

                Krzysztof Wolk and Krzysztof Marasek……101-104

The NAIST English speech recognition system for IWSLT 2015

                Michael Heck, Quoc Truong Do, Sakriani Sakti, Graham Neubig and Satoshi Nakamura……105-111

Improvement of word alignment models for Vietnamese-to-English translation

                Takahiro Nomura, Hajime Tsukada and Tomoyoshi Akiba……112-116

 

Technical papers

Unsupervised comparable corpora preparation and exploration for bi-lingual translation equivalents

                Krzysztof Wolk and Krzysztof Marasek……118-125

Applying cross-entropy difference for selecting parallel training data from publicly available sources for conversational machine translation

                William Lewis, Christian Federmann and Ying Xin……126-134

Source discriminative word lexicon for translation disambiguation

                Teresa Herrmann, Jan Niehues and Alex Waibel……135-142

Phrase-level estimation for machine translation

                Varvara Logacheva and Lucia Specia……143-150

Improving continuous space language models auxiliary features

                Walid Aransa, Holger Schwenk and Loïc Barrault……151-158

Multifeature modular deep neural network acoustic models

                Kevin Kilgour and Alex Waibel……159-166

Using language adaptive deep neural networks for improved multilingual speech recognition

                Markus Mueller and Alex Waibel……167-172

Punctuation insertion for real-time spoken language translation

                Eunah Cho, Jan Niehues, Kevin Kilgour and Alex Waibel……173-179

Class-based N-gram language difference models for data selection

                Amittai Axelrod, Yogarshi Vyas, Marianna Martindale and Marine Carpuat……180-187

Morphology-aware alignments for translation to and from a synthetic language

                Franck Burlot and François Yvon……188-195

An open-source toolkit for word-level confidence estimation in machine translation

                Christophe Servan, Le Ngoc Tien, Luong Ngoc Quang, Lecouteux Benjamin and Besacier Laurent……196-203

Improving translation of emphasis with pause prediction in speech-to-speech translation systems

                Quoc Truong Do, Sakriani Sakti, Graham Neubig, Tomoki Toda and Satoshi Nakamura……204-208

Evaluation and revision of a speech translation system for healthcare

                Mark Seligman and Mike Dillinger……209-216

Learning segmentations that balance latency versus quality in spoken language translation

                Hassan Shavarani, Maryam Siahbani, Ramtin Mehdizadeh Seraj and Anoop Sarkar……217-224

Development of a Filipino-to-English bidirectional statistical machine translation system that dynamically updates via user feedback

                Joel Ilao, Jasmine Ang, Marc Randell Chan, Paolo Genato and Joyce Uy……225-231

Parser self-training for syntax-based machine translation

                Makoto Morishita, Koichi Akabe, Yuto Hatakoshi, Graham Neubig, Koichiro Yoshino and Satoshi Nakamura……232-239

Risk-aware distribution of SMT outputs for translation of documents targeting many anonymous readers

                Yo Ehara, Masao Utiyama and Eiichiro Sumita……240-247

Inducing bilingual lexicons from small quantities of sentence-aligned phonemic transcriptions

                Oliver Adams, Graham Neubig, Trevor Cohn and Steven Bird……248-255