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
1NICT-5INDICen-ml2018/08/24 14:55:112125------16.56- 0.00 0.00NMTNoBilingual transformer model
2AnuvaadINDICen-ml2018/09/16 03:57:232446------14.23- 0.00 0.00SMTNoSMT with KenLM
3IITP-MTINDICen-ml2018/09/14 20:20:082355------13.50- 0.00 0.00NMTNoTransformer multilingual En-XX
4RGNLPINDICen-ml2018/09/15 21:04:472431------12.75- 0.00 0.00SMTNoSMT system with SRILM Language model
5cvitINDICen-ml2019/03/14 22:56:042632------ 9.22- 0.00 0.00NMTYesmassive-multi + ft
6ORGANIZERINDICen-ml2018/08/24 18:21:412147------ 8.48- 0.00 0.00NMTNoone2multi multilingual NMT with Attention
7cvitINDICen-ml2019/03/14 22:55:232631------ 8.17- 0.00 0.00NMTYesmassive-multi
8ORGANIZERINDICen-ml2018/08/29 14:25:232190------ 8.05- 0.00 0.00NMTNomulti2multi multilingual NMT with Attention
9RGNLPINDICen-ml2018/09/15 20:37:432424------ 7.81- 0.00 0.00NMTNoNMT system with a 2-layer LSTM method
10NICT-5INDICen-ml2018/08/24 14:40:492104------ 7.29- 0.00 0.00NMTNoEn-XX transformer model
11ORGANIZERINDICen-ml2018/08/20 11:12:572005------ 7.24- 0.00 0.00NMTNoNMT with Attention
12NICT-5INDICen-ml2018/08/24 14:59:352130------ 4.87- 0.00 0.00NMTNoXX-XX transformer model

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
1cvitINDICen-ml2019/03/14 22:56:042632------0.517447-0.0000000.000000NMTYesmassive-multi + ft
2IITP-MTINDICen-ml2018/09/14 20:20:082355------0.488103-0.0000000.000000NMTNoTransformer multilingual En-XX
3NICT-5INDICen-ml2018/08/24 14:55:112125------0.486016-0.0000000.000000NMTNoBilingual transformer model
4cvitINDICen-ml2019/03/14 22:55:232631------0.471012-0.0000000.000000NMTYesmassive-multi
5NICT-5INDICen-ml2018/08/24 14:59:352130------0.469563-0.0000000.000000NMTNoXX-XX transformer model
6NICT-5INDICen-ml2018/08/24 14:40:492104------0.464451-0.0000000.000000NMTNoEn-XX transformer model
7RGNLPINDICen-ml2018/09/15 21:04:472431------0.424079-0.0000000.000000SMTNoSMT system with SRILM Language model
8AnuvaadINDICen-ml2018/09/16 03:57:232446------0.422574-0.0000000.000000SMTNoSMT with KenLM
9ORGANIZERINDICen-ml2018/08/24 18:21:412147------0.393021-0.0000000.000000NMTNoone2multi multilingual NMT with Attention
10ORGANIZERINDICen-ml2018/08/29 14:25:232190------0.381486-0.0000000.000000NMTNomulti2multi multilingual NMT with Attention
11ORGANIZERINDICen-ml2018/08/20 11:12:572005------0.363953-0.0000000.000000NMTNoNMT with Attention
12RGNLPINDICen-ml2018/09/15 20:37:432424------0.350811-0.0000000.000000NMTNoNMT system with a 2-layer LSTM method

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
1cvitINDICen-ml2019/03/14 22:56:042632------0.645120-0.0000000.000000NMTYesmassive-multi + ft
2NICT-5INDICen-ml2018/08/24 14:55:112125------0.643510-0.0000000.000000NMTNoBilingual transformer model
3IITP-MTINDICen-ml2018/09/14 20:20:082355------0.635180-0.0000000.000000NMTNoTransformer multilingual En-XX
4cvitINDICen-ml2019/03/14 22:55:232631------0.631570-0.0000000.000000NMTYesmassive-multi
5NICT-5INDICen-ml2018/08/24 14:40:492104------0.616800-0.0000000.000000NMTNoEn-XX transformer model
6NICT-5INDICen-ml2018/08/24 14:59:352130------0.608970-0.0000000.000000NMTNoXX-XX transformer model
7RGNLPINDICen-ml2018/09/15 21:04:472431------0.592290-0.0000000.000000SMTNoSMT system with SRILM Language model
8AnuvaadINDICen-ml2018/09/16 03:57:232446------0.567090-0.0000000.000000SMTNoSMT with KenLM
9ORGANIZERINDICen-ml2018/08/29 14:25:232190------0.541080-0.0000000.000000NMTNomulti2multi multilingual NMT with Attention
10ORGANIZERINDICen-ml2018/08/24 18:21:412147------0.537910-0.0000000.000000NMTNoone2multi multilingual NMT with Attention
11ORGANIZERINDICen-ml2018/08/20 11:12:572005------0.517240-0.0000000.000000NMTNoNMT with Attention
12RGNLPINDICen-ml2018/09/15 20:37:432424------0.440600-0.0000000.000000NMTNoNMT system with a 2-layer LSTM method

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