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
1Bering LabJPCN2ja-zh2021/04/30 12:39:495848-43.98--45.0144.72----NMTYesTransformer Ensemble with additional crawled parallel corpus
2KNU_HyundaiJPCN2ja-zh2019/07/27 08:39:213165-44.09--45.2344.68----NMTYesTransformer(base) + *Used ASPEC corpus* with relative position, bt, r2l rerank, 4-model ensemble(9-check point)
3sarahJPCN2ja-zh2019/07/26 11:40:152983-42.23--43.1942.98----NMTNoTransformer, ensemble of 4 models
4goku20JPCN2ja-zh2020/09/22 00:10:384110-41.93--42.8442.52----NMTNomBART pre-training transformer, ensemble of 3 models
5goku20JPCN2ja-zh2020/09/22 00:12:524111-41.93--42.8442.52----NMTNomBART pre-training transformer, ensemble of 3 models
6ryanJPCN2ja-zh2019/07/25 22:06:172951-41.68--42.6342.26----NMTNoBase Transformer
7goku20JPCN2ja-zh2020/09/21 12:09:424090-40.84--41.7541.43----NMTNomBART pre-training transformer, single model
8sakuraJPCN2ja-zh2024/08/09 00:42:327304-40.60--41.4041.10----NMTNoLLM: Rakuten/RakutenAI-7B-chat Fine-Tuned with JPC Corpus in six direction (En-Ja, Ja-En, Ko-Ja, Ja-Ko, Zh-Ja, Ja-Zh) - Best
9sakuraJPCN2ja-zh2024/08/09 00:44:497305-40.30--41.2040.80----NMTNoLLM: Rakuten/RakutenAI-7B-chat Fine-Tuned with JPC Corpus in six direction (En-Ja, Ja-En, Ko-Ja, Ja-Ko, Zh-Ja, Ja-Zh)
10USTCJPCN2ja-zh2018/08/31 17:00:532203-39.91--40.5340.32-- 0.00 0.00NMTNotensor2tensor, 4 model average, r2l rerank
11ORGANIZERJPCN2ja-zh2018/08/15 18:23:171961-39.14--40.2839.77-- 0.00 0.00NMTNoNMT with Attention
12tpt_watJPCN2ja-zh2021/04/27 01:50:285695-38.76--39.7139.47----SMTNoBase Transformer Model with separate vocabularies, 8k size
13tpt_watJPCN2ja-zh2021/04/27 01:51:045696-38.76--39.7139.47----SMTNoBase Transformer Model with separate vocabularies, 8k size

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
1KNU_HyundaiJPCN2ja-zh2019/07/27 08:39:213165-0.869556--0.8741400.872997----NMTYesTransformer(base) + *Used ASPEC corpus* with relative position, bt, r2l rerank, 4-model ensemble(9-check point)
2Bering LabJPCN2ja-zh2021/04/30 12:39:495848-0.868941--0.8733820.872298----NMTYesTransformer Ensemble with additional crawled parallel corpus
3goku20JPCN2ja-zh2020/09/22 00:10:384110-0.857293--0.8634190.861801----NMTNomBART pre-training transformer, ensemble of 3 models
4goku20JPCN2ja-zh2020/09/22 00:12:524111-0.857293--0.8634190.861801----NMTNomBART pre-training transformer, ensemble of 3 models
5ryanJPCN2ja-zh2019/07/25 22:06:172951-0.857546--0.8625990.861150----NMTNoBase Transformer
6sakuraJPCN2ja-zh2024/08/09 00:42:327304-0.854800--0.8608330.859124----NMTNoLLM: Rakuten/RakutenAI-7B-chat Fine-Tuned with JPC Corpus in six direction (En-Ja, Ja-En, Ko-Ja, Ja-Ko, Zh-Ja, Ja-Zh) - Best
7sarahJPCN2ja-zh2019/07/26 11:40:152983-0.854775--0.8608370.859031----NMTNoTransformer, ensemble of 4 models
8sakuraJPCN2ja-zh2024/08/09 00:44:497305-0.854198--0.8601370.858608----NMTNoLLM: Rakuten/RakutenAI-7B-chat Fine-Tuned with JPC Corpus in six direction (En-Ja, Ja-En, Ko-Ja, Ja-Ko, Zh-Ja, Ja-Zh)
9goku20JPCN2ja-zh2020/09/21 12:09:424090-0.853709--0.8598720.858557----NMTNomBART pre-training transformer, single model
10USTCJPCN2ja-zh2018/08/31 17:00:532203-0.853978--0.8593300.857456--0.0000000.000000NMTNotensor2tensor, 4 model average, r2l rerank
11ORGANIZERJPCN2ja-zh2018/08/15 18:23:171961-0.847486--0.8521610.850707--0.0000000.000000NMTNoNMT with Attention
12tpt_watJPCN2ja-zh2021/04/27 01:50:285695-0.844570--0.8498190.848185----SMTNoBase Transformer Model with separate vocabularies, 8k size
13tpt_watJPCN2ja-zh2021/04/27 01:51:045696-0.844570--0.8498190.848185----SMTNoBase Transformer Model with separate vocabularies, 8k size

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
1Bering LabJPCN2ja-zh2021/04/30 12:39:495848-0.893837--0.8938370.893837----NMTYesTransformer Ensemble with additional crawled parallel corpus
2tpt_watJPCN2ja-zh2021/04/27 01:50:285695-0.888029--0.8880290.888029----SMTNoBase Transformer Model with separate vocabularies, 8k size
3tpt_watJPCN2ja-zh2021/04/27 01:51:045696-0.888029--0.8880290.888029----SMTNoBase Transformer Model with separate vocabularies, 8k size
4ORGANIZERJPCN2ja-zh2018/08/15 18:23:171961-0.000000--0.0000000.000000--0.0000000.000000NMTNoNMT with Attention
5USTCJPCN2ja-zh2018/08/31 17:00:532203-0.000000--0.0000000.000000--0.0000000.000000NMTNotensor2tensor, 4 model average, r2l rerank
6ryanJPCN2ja-zh2019/07/25 22:06:172951-0.000000--0.0000000.000000----NMTNoBase Transformer
7sarahJPCN2ja-zh2019/07/26 11:40:152983-0.000000--0.0000000.000000----NMTNoTransformer, ensemble of 4 models
8KNU_HyundaiJPCN2ja-zh2019/07/27 08:39:213165-0.000000--0.0000000.000000----NMTYesTransformer(base) + *Used ASPEC corpus* with relative position, bt, r2l rerank, 4-model ensemble(9-check point)
9goku20JPCN2ja-zh2020/09/21 12:09:424090-0.000000--0.0000000.000000----NMTNomBART pre-training transformer, single model
10goku20JPCN2ja-zh2020/09/22 00:10:384110-0.000000--0.0000000.000000----NMTNomBART pre-training transformer, ensemble of 3 models
11goku20JPCN2ja-zh2020/09/22 00:12:524111-0.000000--0.0000000.000000----NMTNomBART pre-training transformer, ensemble of 3 models
12sakuraJPCN2ja-zh2024/08/09 00:42:327304-0.000000--0.0000000.000000----NMTNoLLM: Rakuten/RakutenAI-7B-chat Fine-Tuned with JPC Corpus in six direction (En-Ja, Ja-En, Ko-Ja, Ja-Ko, Zh-Ja, Ja-Zh) - Best
13sakuraJPCN2ja-zh2024/08/09 00:44:497305-0.000000--0.0000000.000000----NMTNoLLM: Rakuten/RakutenAI-7B-chat Fine-Tuned with JPC Corpus in six direction (En-Ja, Ja-En, Ko-Ja, Ja-Ko, Zh-Ja, Ja-Zh)

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
1sarahJPCN2ja-zh2019/07/26 11:40:152983UnderwayNMTNoTransformer, ensemble of 4 models
2KNU_HyundaiJPCN2ja-zh2019/07/27 08:39:213165UnderwayNMTYesTransformer(base) + *Used ASPEC corpus* with relative position, bt, r2l rerank, 4-model ensemble(9-check point)

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