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
1EHRHINDENhi-ja2016/08/17 18:03:321167 7.8110.12 8.11---- 0.00 0.00 0.00SMTYesPBSMT with phrase table pivoting and pivot language (en) reordering. User dictionary and TED based LM are used.
2EHRHINDENhi-ja2016/08/18 13:40:051179 7.66 9.80 7.95---- 0.00 0.00 0.00SMTYesPBSMT with sentence level pivoting and pivot language (en) reordering. User dictionary and TED based LM are used.
3EHRHINDENhi-ja2016/08/20 16:37:151250 7.47 9.68 7.58---- 0.00 0.00 0.00SMTYesPBSMT with sentence level pivoting without pivot language (en) reordering. User dictionary and TED based LM are used.
4ORGANIZERHINDENhi-ja2016/08/01 15:08:091064 6.6010.42 7.47---- 0.00 0.00 0.00OtherYesOnline A (2016)
5ORGANIZERHINDENhi-ja2016/08/01 15:10:581065 5.70 8.91 6.38---- 0.00 0.00 0.00OtherYesOnline B (2016)
6EHRHINDENhi-ja2016/08/18 13:33:431178 2.36 4.04 2.52---- 0.00 0.00 0.00SMTYesPBSMT with user dictionary and TED based LM.
7ORGANIZERHINDENhi-ja2016/08/20 17:26:481251 2.05 4.17 2.42---- 0.00 0.00 0.00SMTNoPhrase-based SMT
8ORGANIZERHINDENhi-ja2018/11/13 14:58:332568 1.52 3.27 1.84----- 0.00 0.00NMTNoNMT with Attention

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
1EHRHINDENhi-ja2016/08/18 13:40:0511790.5859530.6181060.597490----0.0000000.0000000.000000SMTYesPBSMT with sentence level pivoting and pivot language (en) reordering. User dictionary and TED based LM are used.
2EHRHINDENhi-ja2016/08/20 16:37:1512500.5823440.6138320.588733----0.0000000.0000000.000000SMTYesPBSMT with sentence level pivoting without pivot language (en) reordering. User dictionary and TED based LM are used.
3EHRHINDENhi-ja2016/08/17 18:03:3211670.5792850.6170980.588723----0.0000000.0000000.000000SMTYesPBSMT with phrase table pivoting and pivot language (en) reordering. User dictionary and TED based LM are used.
4ORGANIZERHINDENhi-ja2016/08/01 15:08:0910640.5651090.5978630.576725----0.0000000.0000000.000000OtherYesOnline A (2016)
5ORGANIZERHINDENhi-ja2016/08/01 15:10:5810650.5604860.5895580.571670----0.0000000.0000000.000000OtherYesOnline B (2016)
6EHRHINDENhi-ja2016/08/18 13:33:4311780.4401990.4885040.450220----0.0000000.0000000.000000SMTYesPBSMT with user dictionary and TED based LM.
7ORGANIZERHINDENhi-ja2016/08/20 17:26:4812510.4401220.4964020.461763----0.0000000.0000000.000000SMTNoPhrase-based SMT
8ORGANIZERHINDENhi-ja2018/11/13 14:58:3325680.3384880.4035520.365122-----0.0000000.000000NMTNoNMT with Attention

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
1ORGANIZERHINDENhi-ja2016/08/01 15:08:0910640.4952700.4952700.495270----0.0000000.0000000.000000OtherYesOnline A (2016)
2EHRHINDENhi-ja2016/08/18 13:40:0511790.4731200.4731200.473120----0.0000000.0000000.000000SMTYesPBSMT with sentence level pivoting and pivot language (en) reordering. User dictionary and TED based LM are used.
3ORGANIZERHINDENhi-ja2016/08/01 15:10:5810650.4714500.4714500.471450----0.0000000.0000000.000000OtherYesOnline B (2016)
4EHRHINDENhi-ja2016/08/17 18:03:3211670.4681400.4681400.468140----0.0000000.0000000.000000SMTYesPBSMT with phrase table pivoting and pivot language (en) reordering. User dictionary and TED based LM are used.
5EHRHINDENhi-ja2016/08/20 16:37:1512500.4549200.4549200.454920----0.0000000.0000000.000000SMTYesPBSMT with sentence level pivoting without pivot language (en) reordering. User dictionary and TED based LM are used.
6EHRHINDENhi-ja2016/08/18 13:33:4311780.3627700.3627700.362770----0.0000000.0000000.000000SMTYesPBSMT with user dictionary and TED based LM.
7ORGANIZERHINDENhi-ja2016/08/20 17:26:4812510.3609100.3609100.360910----0.0000000.0000000.000000SMTNoPhrase-based SMT
8ORGANIZERHINDENhi-ja2018/11/13 14:58:3325680.3489100.3489100.348910-----0.0000000.000000NMTNoNMT with Attention

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
1ORGANIZERHINDENhi-ja2016/08/01 15:08:09106439.750OtherYesOnline A (2016)
2ORGANIZERHINDENhi-ja2016/08/01 15:10:58106517.750OtherYesOnline B (2016)
3EHRHINDENhi-ja2016/08/17 18:03:32116713.750SMTYesPBSMT with phrase table pivoting and pivot language (en) reordering. User dictionary and TED based LM are used.
4EHRHINDENhi-ja2016/08/18 13:40:05117910.000SMTYesPBSMT with sentence level pivoting and pivot language (en) reordering. User dictionary and TED based LM are used.

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