WAT 2016

The 3rd Workshop on Asian Translation

Baseline Systems

Tools

For all subtasks

• Moses version 2.1.1
• GIZA++ version 1.0.7

For Japanese segmentation

• Juman version 7.0

For Chinese segmentation

• Stanford Word Segmenter version 2014-01-04
  (Using Chinese Penn Treebank (CTB) model)

For Korean segmentation

• mecab-ko
  (https://bitbucket.org/eunjeon/mecab-ko/downloads/mecab-0.996-ko-0.9.1.tar.gz)
  (https://bitbucket.org/eunjeon/mecab-ko-dic/downloads/mecab-ko-dic-1.6.1-20140814.tar.gz)
  Install procedure
  

For Hindi segmentation

• Indic NLP Library: For tokenization, normalization and script conversion

For English and Chinese parsing

• Berkeley parser [for java 1.7]

For English Pre-reordering (English-Hindi Task)

• English Preorderer

For character conversion

• scripts

Java

• Version 7 Update 60 (JDK, JRE)
  (For Stanford Word Segmenter and Berkeley parser)

JST (Japan Science and Technology Agency)
NICT (National Institute of Information and Communications Technology)
Kyoto University
Last Modified: 2016-06-11