NICT_LOGO.JPG KYOTO-U_LOGO.JPG

WAT

The Workshop on Asian Translation
Evaluation Results

[EVALUATION RESULTS TOP] | [BLEU] | [RIBES] | [AMFM] | [HUMAN (WAT2019)] | [HUMAN (WAT2018)] | [HUMAN (WAT2017)] | [HUMAN (WAT2016)] | [HUMAN (WAT2015)] | [HUMAN (WAT2014)] | [EVALUATION RESULTS USAGE POLICY]

BLEU


# Team Task Date/Time DataID BLEU
Method
Other
Resources
System
Description
juman kytea mecab moses-
tokenizer
stanford-
segmenter-
ctb
stanford-
segmenter-
pku
indic-
tokenizer
unuse myseg kmseg
1RGNLPINDICen-ur2018/09/15 21:14:192434------32.86- 0.00 0.00SMTNoSMT system with KENLM Language model
2NICT-5INDICen-ur2018/08/24 15:03:092140------29.05- 0.00 0.00NMTNoXX-XX transformer model
3NICT-5INDICen-ur2018/08/24 14:52:092117------27.05- 0.00 0.00NMTNoEn-XX transformer model
4AnuvaadINDICen-ur2018/09/16 00:46:332442------21.62- 0.00 0.00SMTNoSMT with KenLM
5IITP-MTINDICen-ur2018/09/14 20:32:232358------21.48- 0.00 0.00NMTNoTransformer multilingual En-XX
6RGNLPINDICen-ur2018/09/15 20:45:192427------21.17- 0.00 0.00NMTNoNMT system with a 2-layer LSTM method
7NICT-5INDICen-ur2018/08/24 14:51:532116------20.21- 0.00 0.00NMTNoBilingual transformer model
8cvitINDICen-ur2019/03/14 23:10:442639------19.51- 0.00 0.00NMTYesmassive-multi + ft
9cvitINDICen-ur2019/03/14 23:09:422638------16.56- 0.00 0.00NMTYesmassive-multi
10ORGANIZERINDICen-ur2018/08/24 18:26:522150------15.25- 0.00 0.00NMTNoone2multi multilingual NMT with Attention
11ORGANIZERINDICen-ur2018/08/29 14:34:292196------14.90- 0.00 0.00NMTNomulti2multi multilingual NMT with Attention
12ORGANIZERINDICen-ur2018/08/20 11:24:062011------ 9.13- 0.00 0.00NMTNoNMT with Attention

Notice:

Back to top

RIBES


# Team Task Date/Time DataID RIBES
Method
Other
Resources
System
Description
juman kytea mecab moses-
tokenizer
stanford-
segmenter-
ctb
stanford-
segmenter-
pku
indic-
tokenizer
unuse myseg kmseg
1NICT-5INDICen-ur2018/08/24 15:03:092140------0.672144-0.0000000.000000NMTNoXX-XX transformer model
2RGNLPINDICen-ur2018/09/15 21:14:192434------0.669589-0.0000000.000000SMTNoSMT system with KENLM Language model
3cvitINDICen-ur2019/03/14 23:10:442639------0.657035-0.0000000.000000NMTYesmassive-multi + ft
4cvitINDICen-ur2019/03/14 23:09:422638------0.635709-0.0000000.000000NMTYesmassive-multi
5NICT-5INDICen-ur2018/08/24 14:52:092117------0.635266-0.0000000.000000NMTNoEn-XX transformer model
6AnuvaadINDICen-ur2018/09/16 00:46:332442------0.628279-0.0000000.000000SMTNoSMT with KenLM
7IITP-MTINDICen-ur2018/09/14 20:32:232358------0.627308-0.0000000.000000NMTNoTransformer multilingual En-XX
8ORGANIZERINDICen-ur2018/08/24 18:26:522150------0.613106-0.0000000.000000NMTNoone2multi multilingual NMT with Attention
9ORGANIZERINDICen-ur2018/08/29 14:34:292196------0.611790-0.0000000.000000NMTNomulti2multi multilingual NMT with Attention
10RGNLPINDICen-ur2018/09/15 20:45:192427------0.600133-0.0000000.000000NMTNoNMT system with a 2-layer LSTM method
11NICT-5INDICen-ur2018/08/24 14:51:532116------0.544527-0.0000000.000000NMTNoBilingual transformer model
12ORGANIZERINDICen-ur2018/08/20 11:24:062011------0.494894-0.0000000.000000NMTNoNMT with Attention

Notice:

Back to top

AMFM


# Team Task Date/Time DataID AMFM
Method
Other
Resources
System
Description
juman kytea mecab moses-
tokenizer
stanford-
segmenter-
ctb
stanford-
segmenter-
pku
indic-
tokenizer
unuse myseg kmseg
1NICT-5INDICen-ur2018/08/24 15:03:092140------0.559600-0.0000000.000000NMTNoXX-XX transformer model
2RGNLPINDICen-ur2018/09/15 21:14:192434------0.550110-0.0000000.000000SMTNoSMT system with KENLM Language model
3cvitINDICen-ur2019/03/14 23:10:442639------0.537590-0.0000000.000000NMTYesmassive-multi + ft
4AnuvaadINDICen-ur2018/09/16 00:46:332442------0.534550-0.0000000.000000SMTNoSMT with KenLM
5cvitINDICen-ur2019/03/14 23:09:422638------0.513210-0.0000000.000000NMTYesmassive-multi
6NICT-5INDICen-ur2018/08/24 14:52:092117------0.501810-0.0000000.000000NMTNoEn-XX transformer model
7IITP-MTINDICen-ur2018/09/14 20:32:232358------0.495020-0.0000000.000000NMTNoTransformer multilingual En-XX
8ORGANIZERINDICen-ur2018/08/29 14:34:292196------0.491680-0.0000000.000000NMTNomulti2multi multilingual NMT with Attention
9ORGANIZERINDICen-ur2018/08/24 18:26:522150------0.489650-0.0000000.000000NMTNoone2multi multilingual NMT with Attention
10RGNLPINDICen-ur2018/09/15 20:45:192427------0.478180-0.0000000.000000NMTNoNMT system with a 2-layer LSTM method
11NICT-5INDICen-ur2018/08/24 14:51:532116------0.424800-0.0000000.000000NMTNoBilingual transformer model
12ORGANIZERINDICen-ur2018/08/20 11:24:062011------0.392370-0.0000000.000000NMTNoNMT with Attention

Notice:

Back to top

HUMAN (WAT2019)


# Team Task Date/Time DataID HUMAN
Method
Other
Resources
System
Description

Notice:
Back to top

HUMAN (WAT2018)


# Team Task Date/Time DataID HUMAN
Method
Other
Resources
System
Description

Notice:
Back to top

HUMAN (WAT2017)


# Team Task Date/Time DataID HUMAN
Method
Other
Resources
System
Description

Notice:
Back to top

HUMAN (WAT2016)


# Team Task Date/Time DataID HUMAN
Method
Other
Resources
System
Description

Notice:
Back to top

HUMAN (WAT2015)


# Team Task Date/Time DataID HUMAN
Method
Other
Resources
System
Description

Notice:
Back to top

HUMAN (WAT2014)


# Team Task Date/Time DataID HUMAN
Method
Other
Resources
System
Description

Notice:
Back to top

EVALUATION RESULTS USAGE POLICY

When you use the WAT evaluation results for any purpose such as:
- writing technical papers,
- making presentations about your system,
- advertising your MT system to the customers,
you can use the information about translation directions, scores (including both automatic and human evaluations) and ranks of your system among others. You can also use the scores of the other systems, but you MUST anonymize the other system's names. In addition, you can show the links (URLs) to the WAT evaluation result pages.

NICT (National Institute of Information and Communications Technology)
Kyoto University
Last Modified: 2018-08-02