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
1cvitINDICbn-en2019/03/23 12:36:322660---20.19---- 0.00 0.00NMTYes
2IITP-MTINDICbn-en2018/09/14 19:45:112346---20.05---- 0.00 0.00NMTNoTransformer multilingual XX-En
3cvitINDICbn-en2019/03/14 21:57:232622---19.58---- 0.00 0.00NMTYesmassive-multi + ft
4NICT-5INDICbn-en2018/08/22 19:03:012060---19.17---- 0.00 0.00NMTNoBilingual transformer model
5cvitINDICbn-en2019/03/22 05:41:562653---18.99---- 0.00 0.00NMTNomay to en (Transformer) - detokenized
6NICT-5INDICbn-en2018/09/07 14:27:152237---18.82---- 0.00 0.00NMTNoUnified Source vocabulary by orthography mapping. XX-EN model.
7cvitINDICbn-en2019/03/22 05:26:032649---18.53---- 0.00 0.00NMTNomany to en (Transformer)
8NICT-5INDICbn-en2018/08/22 19:05:382063---18.03---- 0.00 0.00NMTNoXX-En transformer model
9cvitINDICbn-en2019/03/14 21:47:232615---17.35---- 0.00 0.00NMTYesmassive-multi
10NICT-5INDICbn-en2018/08/24 14:58:302126---16.68---- 0.00 0.00NMTNoXX-XX transformer model
11ORGANIZERINDICbn-en2018/08/24 14:34:362098---16.62---- 0.00 0.00NMTNomulti2one multilingual NMT with Attention
12ORGANIZERINDICbn-en2018/08/20 11:09:172002---15.99---- 0.00 0.00NMTNoNMT with Attention
13ORGANIZERINDICbn-en2018/08/29 14:11:092187---15.91---- 0.00 0.00NMTNomulti2multi multilingual NMT with Attention
14AnuvaadINDICbn-en2018/09/15 20:08:072420---14.17---- 0.00 0.00SMTNoSMT with KenLM
15AnuvaadINDICbn-en2018/09/15 18:00:102405---13.98---- 0.00 0.00SMTNoSMT XX-En
16RGNLPINDICbn-en2018/09/15 03:06:072380---12.19---- 0.00 0.00NMTNoNMT system with a 2-layer LSTM method
17RGNLPINDICbn-en2018/09/15 02:21:512366---11.58---- 0.00 0.00SMTNoSMT system with KENLM Language model
18RGNLPINDICbn-en2018/09/15 02:47:142373---11.07---- 0.00 0.00SMTNoSMT system with SRILM Language model

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
1cvitINDICbn-en2019/03/23 12:36:322660---0.759463----0.0000000.000000NMTYes
2cvitINDICbn-en2019/03/14 21:57:232622---0.759214----0.0000000.000000NMTYesmassive-multi + ft
3cvitINDICbn-en2019/03/22 05:41:562653---0.756935----0.0000000.000000NMTNomay to en (Transformer) - detokenized
4NICT-5INDICbn-en2018/09/07 14:27:152237---0.747661----0.0000000.000000NMTNoUnified Source vocabulary by orthography mapping. XX-EN model.
5cvitINDICbn-en2019/03/22 05:26:032649---0.747374----0.0000000.000000NMTNomany to en (Transformer)
6IITP-MTINDICbn-en2018/09/14 19:45:112346---0.742869----0.0000000.000000NMTNoTransformer multilingual XX-En
7NICT-5INDICbn-en2018/08/22 19:05:382063---0.742534----0.0000000.000000NMTNoXX-En transformer model
8cvitINDICbn-en2019/03/14 21:47:232615---0.739462----0.0000000.000000NMTYesmassive-multi
9NICT-5INDICbn-en2018/08/24 14:58:302126---0.739000----0.0000000.000000NMTNoXX-XX transformer model
10NICT-5INDICbn-en2018/08/22 19:03:012060---0.738440----0.0000000.000000NMTNoBilingual transformer model
11ORGANIZERINDICbn-en2018/08/24 14:34:362098---0.729427----0.0000000.000000NMTNomulti2one multilingual NMT with Attention
12ORGANIZERINDICbn-en2018/08/29 14:11:092187---0.727120----0.0000000.000000NMTNomulti2multi multilingual NMT with Attention
13ORGANIZERINDICbn-en2018/08/20 11:09:172002---0.725286----0.0000000.000000NMTNoNMT with Attention
14RGNLPINDICbn-en2018/09/15 03:06:072380---0.704033----0.0000000.000000NMTNoNMT system with a 2-layer LSTM method
15AnuvaadINDICbn-en2018/09/15 20:08:072420---0.689672----0.0000000.000000SMTNoSMT with KenLM
16AnuvaadINDICbn-en2018/09/15 18:00:102405---0.669154----0.0000000.000000SMTNoSMT XX-En
17RGNLPINDICbn-en2018/09/15 02:21:512366---0.663523----0.0000000.000000SMTNoSMT system with KENLM Language model
18RGNLPINDICbn-en2018/09/15 02:47:142373---0.661561----0.0000000.000000SMTNoSMT system with SRILM Language model

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
1cvitINDICbn-en2019/03/14 21:57:232622---0.529720----0.0000000.000000NMTYesmassive-multi + ft
2cvitINDICbn-en2019/03/23 12:36:322660---0.527580----0.0000000.000000NMTYes
3cvitINDICbn-en2019/03/22 05:26:032649---0.524490----0.0000000.000000NMTNomany to en (Transformer)
4cvitINDICbn-en2019/03/22 05:41:562653---0.524490----0.0000000.000000NMTNomay to en (Transformer) - detokenized
5IITP-MTINDICbn-en2018/09/14 19:45:112346---0.523800----0.0000000.000000NMTNoTransformer multilingual XX-En
6NICT-5INDICbn-en2018/08/22 19:03:012060---0.516930----0.0000000.000000NMTNoBilingual transformer model
7NICT-5INDICbn-en2018/09/07 14:27:152237---0.512160----0.0000000.000000NMTNoUnified Source vocabulary by orthography mapping. XX-EN model.
8cvitINDICbn-en2019/03/14 21:47:232615---0.510210----0.0000000.000000NMTYesmassive-multi
9NICT-5INDICbn-en2018/08/24 14:58:302126---0.504860----0.0000000.000000NMTNoXX-XX transformer model
10NICT-5INDICbn-en2018/08/22 19:05:382063---0.501980----0.0000000.000000NMTNoXX-En transformer model
11ORGANIZERINDICbn-en2018/08/29 14:11:092187---0.498530----0.0000000.000000NMTNomulti2multi multilingual NMT with Attention
12ORGANIZERINDICbn-en2018/08/24 14:34:362098---0.491570----0.0000000.000000NMTNomulti2one multilingual NMT with Attention
13ORGANIZERINDICbn-en2018/08/20 11:09:172002---0.483240----0.0000000.000000NMTNoNMT with Attention
14RGNLPINDICbn-en2018/09/15 02:47:142373---0.482310----0.0000000.000000SMTNoSMT system with SRILM Language model
15RGNLPINDICbn-en2018/09/15 03:06:072380---0.482010----0.0000000.000000NMTNoNMT system with a 2-layer LSTM method
16RGNLPINDICbn-en2018/09/15 02:21:512366---0.477770----0.0000000.000000SMTNoSMT system with KENLM Language model
17AnuvaadINDICbn-en2018/09/15 20:08:072420---0.454990----0.0000000.000000SMTNoSMT with KenLM
18AnuvaadINDICbn-en2018/09/15 18:00:102405---0.447900----0.0000000.000000SMTNoSMT XX-En

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

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