Overview of the 3rd Workshop on Asian Translation

This paper presents the results of the shared tasks from the 3rd workshop on Asian translation (WAT2016) including J↔E, J↔C scientific paper translation subtasks, C↔J, K↔J, E↔J patent translation subtasks, I↔E newswire subtasks and H↔E, H↔J mixed domain subtasks. For the WAT2016, 15 institutions participated in the shared tasks. About 500 translation results have been submitted to the automatic evaluation server, and selected submissions were manually evaluated.

[1]  Graham Neubig,et al.  Lexicons and Minimum Risk Training for Neural Machine Translation: NAIST-CMU at WAT2016 , 2016, WAT@COLING.

[2]  Chenhui Chu,et al.  Kyoto University Participation to WAT 2016 , 2016, COLING 2016.

[3]  Satoshi Nakamura,et al.  Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015 , 2015, WAT.

[4]  Yufeng Chen,et al.  System Description of bjtu_nlp Neural Machine Translation System , 2016, WAT@COLING.

[5]  Dan Klein,et al.  Learning Accurate, Compact, and Interpretable Tree Annotation , 2006, ACL.

[6]  Terumasa Ehara System Combination of RBMT plus SPE and Preordering plus SMT , 2015, WAT.

[7]  Graham Neubig,et al.  Pointwise Prediction for Robust, Adaptable Japanese Morphological Analysis , 2011, ACL.

[8]  Jun-Seok Kim,et al.  NAVER Machine Translation System for WAT 2015 , 2015, WAT.

[9]  Wei Yang,et al.  Sampling-based Alignment and Hierarchical Sub-sentential Alignment in Chinese-Japanese Translation of Patents , 2015, WAT.

[10]  Daniel Jurafsky,et al.  A Conditional Random Field Word Segmenter for Sighan Bakeoff 2005 , 2005, IJCNLP.

[11]  Mamoru Komachi,et al.  Source Phrase Segmentation and Translation for Japanese-English Translation Using Dependency Structure , 2015, WAT.

[12]  Philipp Koehn,et al.  Scalable Modified Kneser-Ney Language Model Estimation , 2013, ACL.

[13]  Marcin Junczys-Dowmunt,et al.  Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions , 2016, IWSLT.

[14]  Kevin Duh,et al.  Automatic Evaluation of Translation Quality for Distant Language Pairs , 2010, EMNLP.

[15]  Raphael Shu,et al.  Residual Stacking of RNNs for Neural Machine Translation , 2016, WAT@COLING.

[16]  Jacob Cohen,et al.  Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. , 1968 .

[17]  Katsuhito Sudoh,et al.  Chinese-to-Japanese Patent Machine Translation based on Syntactic Pre-ordering forWAT 2015 , 2015, WAT.

[18]  Pushpak Bhattacharyya,et al.  IITP English-Hindi Machine Translation System at WAT 2016 , 2016, WAT@COLING.

[19]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[20]  Haizhou Li,et al.  Adequacy–Fluency Metrics: Evaluating MT in the Continuous Space Model Framework , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[21]  Lu Bai,et al.  A Dependency-to-String Model for Chinese-Japanese SMT System , 2015, WAT.

[22]  Zhongyuan Zhu,et al.  Evaluating Neural Machine Translation in English-Japanese Task , 2015, WAT.

[23]  Eiichiro Sumita,et al.  NICT-2 Translation System for WAT2016: Applying Domain Adaptation to Phrase-based Statistical Machine Translation , 2016, WAT@COLING.

[24]  Taku Kudo,et al.  MeCab : Yet Another Part-of-Speech and Morphological Analyzer , 2005 .

[25]  Josef van Genabith,et al.  An Awkward Disparity between BLEU / RIBES Scores and Human Judgements in Machine Translation , 2015, WAT.

[26]  Liling Tan,et al.  Faster and Lighter Phrase-based Machine Translation Baseline , 2016, WAT@COLING.

[27]  Pushpak Bhattacharyya,et al.  IIT Bombay's English-Indonesian submission at WAT: Integrating Neural Language Models with SMT , 2016, WAT@COLING.

[28]  Mamoru Komachi,et al.  Controlling the Voice of a Sentence in Japanese-to-English Neural Machine Translation , 2016, WAT@COLING.

[29]  Wei Yang,et al.  Improving Patent Translation using Bilingual Term Extraction and Re-tokenization for Chinese-Japanese , 2016, WAT@COLING.

[30]  Terumasa Ehara Translation systems and experimental results of the EHR group for WAT2016 tasks , 2016, WAT@COLING.

[31]  Graham Neubig,et al.  Overview of the 2nd Workshop on Asian Translation , 2015, WAT.

[32]  Philipp Koehn,et al.  A unified framework for phrase-based, hierarchical, and syntax-based statistical machine translation , 2009, IWSLT.

[33]  M. Utiyama,et al.  A Japanese-English patent parallel corpus , 2007, MTSUMMIT.

[34]  Yoshimasa Tsuruoka,et al.  Character-based Decoding in Tree-to-Sequence Attention-based Neural Machine Translation , 2016, WAT@COLING.

[35]  Yoshimasa Tsuruoka,et al.  Domain Adaptation and Attention-Based Unknown Word Replacement in Chinese-to-Japanese Neural Machine Translation , 2016, WAT@COLING.

[36]  Masao Utiyama,et al.  NICT at WAT 2015 , 2015, WAT.

[37]  Satoshi Kinoshita,et al.  Translation Using JAPIO Patent Corpora: JAPIO at WAT2016 , 2016, WAT@COLING.

[38]  Satoshi Sonoh,et al.  Toshiba MT System Description for the WAT2015 Workshop , 2015 .

[39]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[40]  Eiichiro Sumita,et al.  Overview of the 1st Workshop on Asian Translation , 2014, WAT.

[41]  Chenhui Chu,et al.  KyotoEBMT System Description for the 2nd Workshop on Asian Translation , 2015, WAT.

[42]  J. Fleiss Measuring nominal scale agreement among many raters. , 1971 .

[43]  Philipp Koehn,et al.  Statistical Significance Tests for Machine Translation Evaluation , 2004, EMNLP.