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
1ORGANIZERINDICen-hi2018/08/20 11:10:372003------20.78- 0.00 0.00NMTNoNMT with Attention
2NICT-5INDICen-hi2018/08/22 19:05:042062------26.35- 0.00 0.00SMTNoBilingual transformer model
3NICT-5INDICen-hi2018/08/22 19:09:342067------29.65- 0.00 0.00NMTNoEn-XX transformer model
4NICT-5INDICen-hi2018/08/24 14:59:002128------26.59- 0.00 0.00NMTNoXX-XX transformer model
5ORGANIZERINDICen-hi2018/08/24 18:20:352146------23.27- 0.00 0.00NMTNoone2multi multilingual NMT with Attention
6ORGANIZERINDICen-hi2018/08/29 14:12:512188------22.24- 0.00 0.00NMTNomulti2multi multilingual NMT with Attention
7IITP-MTINDICen-hi2018/09/14 20:18:112354------26.60- 0.00 0.00NMTNoTransformer multilingual En-XX
8RGNLPINDICen-hi2018/09/15 19:02:502417------44.08- 0.00 0.00SMTNoSMT system with KENLM Language model
9RGNLPINDICen-hi2018/09/15 20:30:182422------22.50- 0.00 0.00NMTNoNMT system with a 2-layer LSTM method
10AnuvaadINDICen-hi2018/09/16 02:47:442445------26.49- 0.00 0.00SMTNoSMT with KenLM
11cvitINDICen-hi2018/10/18 14:05:552537------21.32- 0.00 0.00NMTYes
12cvitINDICen-hi2019/03/14 22:49:252629------20.72- 0.00 0.00NMTYesmassive-multi
13cvitINDICen-hi2019/03/14 22:53:452630------26.25- 0.00 0.00NMTYesmassive-multi + ft
14cvitINDICen-hi2019/03/23 17:12:472667------27.09- 0.00 0.00NMTYesmassive-multi e270

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
1ORGANIZERINDICen-hi2018/08/20 11:10:372003------0.682944-0.0000000.000000NMTNoNMT with Attention
2NICT-5INDICen-hi2018/08/22 19:05:042062------0.693875-0.0000000.000000SMTNoBilingual transformer model
3NICT-5INDICen-hi2018/08/22 19:09:342067------0.721379-0.0000000.000000NMTNoEn-XX transformer model
4NICT-5INDICen-hi2018/08/24 14:59:002128------0.734027-0.0000000.000000NMTNoXX-XX transformer model
5ORGANIZERINDICen-hi2018/08/24 18:20:352146------0.709586-0.0000000.000000NMTNoone2multi multilingual NMT with Attention
6ORGANIZERINDICen-hi2018/08/29 14:12:512188------0.705747-0.0000000.000000NMTNomulti2multi multilingual NMT with Attention
7IITP-MTINDICen-hi2018/09/14 20:18:112354------0.722756-0.0000000.000000NMTNoTransformer multilingual En-XX
8RGNLPINDICen-hi2018/09/15 19:02:502417------0.751187-0.0000000.000000SMTNoSMT system with KENLM Language model
9RGNLPINDICen-hi2018/09/15 20:30:182422------0.678207-0.0000000.000000NMTNoNMT system with a 2-layer LSTM method
10AnuvaadINDICen-hi2018/09/16 02:47:442445------0.692385-0.0000000.000000SMTNoSMT with KenLM
11cvitINDICen-hi2018/10/18 14:05:552537------0.714474-0.0000000.000000NMTYes
12cvitINDICen-hi2019/03/14 22:49:252629------0.712607-0.0000000.000000NMTYesmassive-multi
13cvitINDICen-hi2019/03/14 22:53:452630------0.740006-0.0000000.000000NMTYesmassive-multi + ft
14cvitINDICen-hi2019/03/23 17:12:472667------0.745230-0.0000000.000000NMTYesmassive-multi e270

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
1ORGANIZERINDICen-hi2018/08/20 11:10:372003------0.574960-0.0000000.000000NMTNoNMT with Attention
2NICT-5INDICen-hi2018/08/22 19:05:042062------0.589830-0.0000000.000000SMTNoBilingual transformer model
3NICT-5INDICen-hi2018/08/22 19:09:342067------0.636500-0.0000000.000000NMTNoEn-XX transformer model
4NICT-5INDICen-hi2018/08/24 14:59:002128------0.636900-0.0000000.000000NMTNoXX-XX transformer model
5ORGANIZERINDICen-hi2018/08/24 18:20:352146------0.601800-0.0000000.000000NMTNoone2multi multilingual NMT with Attention
6ORGANIZERINDICen-hi2018/08/29 14:12:512188------0.604040-0.0000000.000000NMTNomulti2multi multilingual NMT with Attention
7IITP-MTINDICen-hi2018/09/14 20:18:112354------0.615620-0.0000000.000000NMTNoTransformer multilingual En-XX
8RGNLPINDICen-hi2018/09/15 19:02:502417------0.698550-0.0000000.000000SMTNoSMT system with KENLM Language model
9RGNLPINDICen-hi2018/09/15 20:30:182422------0.584720-0.0000000.000000NMTNoNMT system with a 2-layer LSTM method
10AnuvaadINDICen-hi2018/09/16 02:47:442445------0.657180-0.0000000.000000SMTNoSMT with KenLM
11cvitINDICen-hi2018/10/18 14:05:552537------0.629380-0.0000000.000000NMTYes
12cvitINDICen-hi2019/03/14 22:49:252629------0.632280-0.0000000.000000NMTYesmassive-multi
13cvitINDICen-hi2019/03/14 22:53:452630------0.652810-0.0000000.000000NMTYesmassive-multi + ft
14cvitINDICen-hi2019/03/23 17:12:472667------0.652180-0.0000000.000000NMTYesmassive-multi e270

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

Notice:
Back to top

HUMAN (WAT2018)


# Team Task Date/Time DataID HUMAN
Method
Other
Resources
System
Description
1NICT-5INDICen-hi2018/08/24 14:59:00212830.750NMTNoXX-XX transformer model
2IITP-MTINDICen-hi2018/09/14 20:18:11235420.500NMTNoTransformer multilingual En-XX
3RGNLPINDICen-hi2018/09/15 19:02:50241715.500SMTNoSMT system with KENLM Language model
4NICT-5INDICen-hi2018/08/22 19:09:34206713.750NMTNoEn-XX transformer model
5AnuvaadINDICen-hi2018/09/16 02:47:44244511.000SMTNoSMT with KenLM
6RGNLPINDICen-hi2018/09/15 20:30:182422-0.250NMTNoNMT system with a 2-layer LSTM method

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