NICT_LOGO.JPG KYOTO-U_LOGO.JPG

WAT

The Workshop on Asian Translation
Evaluation Results

[EVALUATION RESULTS TOP] | [BLEU] | [RIBES] | [AMFM] | [HUMAN (WAT2022)] | [HUMAN (WAT2021)] | [HUMAN (WAT2020)] | [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
1cvitUFALta-en2019/07/23 01:29:242833---30.04------NMTNo
2ORGANIZERUFALta-en2019/07/23 17:09:332861---24.46------NMTNoBaseline. Tensor2Tensor out of the box.
3NICT-5UFALta-en2019/07/23 17:13:352863---27.13------NMTNoFine tuning a pretrained Hi-En model on Ta-En data (Hi-En is external data)
4NLPRLUFALta-en2019/07/26 14:44:033014---23.89------NMTNoNMT with Transformer model
5cvitUFALta-en2019/07/26 17:49:443038---27.14------NMTYes
6NICT-5UFALta-en2019/07/26 18:39:543054---27.81------NMTNoMixed training of a pretrained Hindi-English model. T2t implementation of transformer. (Hi-En is external data)
7cvitUFALta-en2019/07/26 22:14:463077---27.99------NMTYesTransformer trained on UFAL , uses external backtranslated data.
8cvitUFALta-en2020/07/06 03:11:493421---25.32------NMTYesxx-to-en model, uses PIB-V1 data.
9cvitUFALta-en2020/07/06 06:50:413424---18.64------NMTYesMultilingual model (mm-all-iter0)
10cvitUFALta-en2020/07/06 07:01:063425---19.76------NMTYesMultilingual model, uses PIB-V0 data. mm-all-iter1
11cvitUFALta-en2020/07/06 16:28:353426---23.38------NMTYesxx-to-EN model, uses PIB-V0 dataset.
12cvitUFALta-en2020/07/10 04:31:173435---26.08------NMTYesxx-to-en model, uses pib-v2 data

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
1cvitUFALta-en2019/07/23 01:29:242833---0.788588------NMTNo
2ORGANIZERUFALta-en2019/07/23 17:09:332861---0.728999------NMTNoBaseline. Tensor2Tensor out of the box.
3NICT-5UFALta-en2019/07/23 17:13:352863---0.753952------NMTNoFine tuning a pretrained Hi-En model on Ta-En data (Hi-En is external data)
4NLPRLUFALta-en2019/07/26 14:44:033014---0.748829------NMTNoNMT with Transformer model
5cvitUFALta-en2019/07/26 17:49:443038---0.770024------NMTYes
6NICT-5UFALta-en2019/07/26 18:39:543054---0.757494------NMTNoMixed training of a pretrained Hindi-English model. T2t implementation of transformer. (Hi-En is external data)
7cvitUFALta-en2019/07/26 22:14:463077---0.773716------NMTYesTransformer trained on UFAL , uses external backtranslated data.
8cvitUFALta-en2020/07/06 03:11:493421---0.754801------NMTYesxx-to-en model, uses PIB-V1 data.
9cvitUFALta-en2020/07/06 06:50:413424---0.710414------NMTYesMultilingual model (mm-all-iter0)
10cvitUFALta-en2020/07/06 07:01:063425---0.723725------NMTYesMultilingual model, uses PIB-V0 data. mm-all-iter1
11cvitUFALta-en2020/07/06 16:28:353426---0.744086------NMTYesxx-to-EN model, uses PIB-V0 dataset.
12cvitUFALta-en2020/07/10 04:31:173435---0.758641------NMTYesxx-to-en model, uses pib-v2 data

Notice:

Back to top

AMFM


# Team Task Date/Time DataID AMFM
Method
Other
Resources
System
Description
unuse unuse unuse unuse unuse unuse unuse unuse unuse unuse
1cvitUFALta-en2019/07/23 01:29:242833---0.707060------NMTNo
2ORGANIZERUFALta-en2019/07/23 17:09:332861---0.663930------NMTNoBaseline. Tensor2Tensor out of the box.
3NICT-5UFALta-en2019/07/23 17:13:352863---0.681970------NMTNoFine tuning a pretrained Hi-En model on Ta-En data (Hi-En is external data)
4NLPRLUFALta-en2019/07/26 14:44:033014---0.682170------NMTNoNMT with Transformer model
5cvitUFALta-en2019/07/26 17:49:443038---0.693750------NMTYes
6NICT-5UFALta-en2019/07/26 18:39:543054---0.685960------NMTNoMixed training of a pretrained Hindi-English model. T2t implementation of transformer. (Hi-En is external data)
7cvitUFALta-en2019/07/26 22:14:463077---0.698330------NMTYesTransformer trained on UFAL , uses external backtranslated data.
8cvitUFALta-en2020/07/06 03:11:493421---0.691510------NMTYesxx-to-en model, uses PIB-V1 data.
9cvitUFALta-en2020/07/06 06:50:413424---0.655420------NMTYesMultilingual model (mm-all-iter0)
10cvitUFALta-en2020/07/06 07:01:063425---0.662810------NMTYesMultilingual model, uses PIB-V0 data. mm-all-iter1
11cvitUFALta-en2020/07/06 16:28:353426---0.677770------NMTYesxx-to-EN model, uses PIB-V0 dataset.
12cvitUFALta-en2020/07/10 04:31:173435---0.693670------NMTYesxx-to-en model, uses pib-v2 data

Notice:

Back to top

HUMAN (WAT2022)


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

Notice:
Back to top

HUMAN (WAT2021)


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

Notice:
Back to top

HUMAN (WAT2020)


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

Notice:
Back to top

HUMAN (WAT2019)


# Team Task Date/Time DataID HUMAN
Method
Other
Resources
System
Description
1cvitUFALta-en2019/07/23 01:29:242833UnderwayNMTNo
2NICT-5UFALta-en2019/07/23 17:13:352863UnderwayNMTNoFine tuning a pretrained Hi-En model on Ta-En data (Hi-En is external data)
3NLPRLUFALta-en2019/07/26 14:44:033014UnderwayNMTNoNMT with Transformer model
4NICT-5UFALta-en2019/07/26 18:39:543054UnderwayNMTNoMixed training of a pretrained Hindi-English model. T2t implementation of transformer. (Hi-En is external data)
5cvitUFALta-en2019/07/26 22:14:463077UnderwayNMTYesTransformer trained on UFAL , uses external backtranslated data.

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