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
1sarahJPCNzh-ja2019/07/22 14:45:06280246.7748.2147.12-------NMTNoTransformer, single model
2sarahJPCNzh-ja2019/07/25 12:11:56292048.6849.9349.02-------NMTNoTransformer, ensemble of 4 models
3ryanJPCNzh-ja2019/07/25 21:58:10294946.9447.9147.24-------NMTNoBase Transformer
4KNU_HyundaiJPCNzh-ja2019/07/27 08:27:13315251.3351.6551.28-------NMTYesTransformer(base) + *Used ASPEC corpus* with relative position, bt, multi source, r2l rerank, 5-model ensemble
5goku20JPCNzh-ja2020/09/18 17:10:40391548.4449.5248.74-------NMTNoTransformer, ensemble of 3 models
6goku20JPCNzh-ja2020/09/18 17:24:39392548.0949.0648.34-------NMTNomBART pre-training, ensemble of 3 models
7tpt_watJPCNzh-ja2021/04/27 01:40:19568946.8048.0047.06-------NMTNoBase Transformer base trained on a shared 8k vocab
8Bering LabJPCNzh-ja2021/05/04 11:01:52620049.6950.5049.86-------NMTYesTransformer Ensemble with additional crawled parallel corpus
9ORGANIZERJPCNzh-ja2018/08/16 16:06:18199543.7244.3843.72----- 0.00 0.00NMTNoNMT with Attention
10USTCJPCNzh-ja2018/08/31 17:20:53220546.4748.0546.85----- 0.00 0.00NMTNotensor2tensor, 4 model average, r2l rerank
11EHRJPCNzh-ja2018/08/31 18:44:03220945.5546.1545.50----- 0.00 0.00NMTNoSMT reranked NMT

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
1sarahJPCNzh-ja2019/07/22 14:45:0628020.8559690.8541680.855597-------NMTNoTransformer, single model
2sarahJPCNzh-ja2019/07/25 12:11:5629200.8644560.8624650.864049-------NMTNoTransformer, ensemble of 4 models
3ryanJPCNzh-ja2019/07/25 21:58:1029490.8638170.8617160.863362-------NMTNoBase Transformer
4KNU_HyundaiJPCNzh-ja2019/07/27 08:27:1331520.8799160.8779820.879411-------NMTYesTransformer(base) + *Used ASPEC corpus* with relative position, bt, multi source, r2l rerank, 5-model ensemble
5goku20JPCNzh-ja2020/09/18 17:10:4039150.8646830.8631610.864643-------NMTNoTransformer, ensemble of 3 models
6goku20JPCNzh-ja2020/09/18 17:24:3939250.8618580.8598460.861534-------NMTNomBART pre-training, ensemble of 3 models
7tpt_watJPCNzh-ja2021/04/27 01:40:1956890.8640510.8619950.863590-------NMTNoBase Transformer base trained on a shared 8k vocab
8Bering LabJPCNzh-ja2021/05/04 11:01:5262000.8770030.8743270.876659-------NMTYesTransformer Ensemble with additional crawled parallel corpus
9ORGANIZERJPCNzh-ja2018/08/16 16:06:1819950.8526230.8497830.851797-----0.0000000.000000NMTNoNMT with Attention
10USTCJPCNzh-ja2018/08/31 17:20:5322050.8621760.8601120.861670-----0.0000000.000000NMTNotensor2tensor, 4 model average, r2l rerank
11EHRJPCNzh-ja2018/08/31 18:44:0322090.8566770.8537060.856269-----0.0000000.000000NMTNoSMT reranked NMT

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
1sarahJPCNzh-ja2019/07/22 14:45:0628020.0000000.0000000.000000-------NMTNoTransformer, single model
2sarahJPCNzh-ja2019/07/25 12:11:5629200.0000000.0000000.000000-------NMTNoTransformer, ensemble of 4 models
3ryanJPCNzh-ja2019/07/25 21:58:1029490.0000000.0000000.000000-------NMTNoBase Transformer
4KNU_HyundaiJPCNzh-ja2019/07/27 08:27:1331520.0000000.0000000.000000-------NMTYesTransformer(base) + *Used ASPEC corpus* with relative position, bt, multi source, r2l rerank, 5-model ensemble
5goku20JPCNzh-ja2020/09/18 17:10:4039150.0000000.0000000.000000-------NMTNoTransformer, ensemble of 3 models
6goku20JPCNzh-ja2020/09/18 17:24:3939250.0000000.0000000.000000-------NMTNomBART pre-training, ensemble of 3 models
7tpt_watJPCNzh-ja2021/04/27 01:40:1956890.9729170.9729170.972917-------NMTNoBase Transformer base trained on a shared 8k vocab
8Bering LabJPCNzh-ja2021/05/04 11:01:5262000.9755880.9755880.975588-------NMTYesTransformer Ensemble with additional crawled parallel corpus
9ORGANIZERJPCNzh-ja2018/08/16 16:06:1819950.0000000.0000000.000000-----0.0000000.000000NMTNoNMT with Attention
10USTCJPCNzh-ja2018/08/31 17:20:5322050.0000000.0000000.000000-----0.0000000.000000NMTNotensor2tensor, 4 model average, r2l rerank
11EHRJPCNzh-ja2018/08/31 18:44:0322090.0000000.0000000.000000-----0.0000000.000000NMTNoSMT reranked NMT

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
1goku20JPCNzh-ja2020/09/18 17:24:3939254.510NMTNomBART pre-training, ensemble of 3 models

Notice:
Back to top

HUMAN (WAT2019)


# Team Task Date/Time DataID HUMAN
Method
Other
Resources
System
Description
1sarahJPCNzh-ja2019/07/25 12:11:562920UnderwayNMTNoTransformer, ensemble of 4 models
2KNU_HyundaiJPCNzh-ja2019/07/27 08:27:133152UnderwayNMTYesTransformer(base) + *Used ASPEC corpus* with relative position, bt, multi source, r2l rerank, 5-model ensemble

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