Hi,

The paper you should look into for a description of BLEU is
Papineni, Kishore, Salim Roukos, Todd Ward and Wei-Jing Zhu. 2002. BLEU: A 
Method for Automatic Evaluation of Machine Translation. In Proceedings of the 
40th Annual Meeting of the Association of Computational Linguistics (ACL ’02), 
pp. 311–318. Philadelphia, PA.

However, you should not be using BLEU nowadays. For a few good reasons why, 
refer to
Callison-Burch, Chris, Miles Osborne and Philipp Koehn. 2006. Re-evaluating the 
Role of BLEU in Machine Translation Research. In Proceedings of the 11th 
Conference of the European Chapter of the Association of Computational 
Linguistics (EACL ’06), pp. 249–256. Oslo, Norway.

If you plan to use MT in a post-editing scenario, there has been evidence that 
other metrics can give you a better idea of MT performance. For a description 
of the JFS metric, see
Zhechev, Ventsislav. 2014. Analysing the Post-Editing of Machine Translation at 
Autodesk. In Post-editing of Machine Translation: Processes and Applications, 
eds. Sharon O’Brien, Laura Winther Balling, Michael Carl, Michel Simard and 
Lucia Specia, chap. 1, pp. 2–24. Newcastle, UK: Cambridge Scholars Publishing.
(or the earlier, but freely available
Zhechev, Ventsislav. 2012. Machine Translation Infrastructure and Post-editing 
Performance at Autodesk. In Proceedings of the AMTA 2012 Workshop on 
Post-editing Technology and Practice (WPTP ’12), eds. Sharon O’Brien, Michel 
Simard and Lucia Specia. San Diego, CA.)


Cheers,

Dr. Ventsislav Zhechev
Computational Linguist
Platform Architecture and Technologies
Localisation Services

MAIN +41 32 723 91 22
FAX +41 32 723 93 99

http://VentsislavZhechev.eu

Autodesk, Inc.
Rue de Puits-Godet 6
2000 Neuchâtel, Switzerland
www.autodesk.com



23.04.2014, в 07:02, moses-support-requ...@mit.edu написал(а):

> Date: Wed, 23 Apr 2014 10:32:40 +0530
> From: Kalyani Baruah <kajubarua...@gmail.com>
> Subject: [Moses-support] Bleu Score
> To: "moses-support@mit.edu" <moses-support@mit.edu>
> Message-ID:
>       <CAJZ5LDdFk+4u0bjpkzEmvbySy7kufkoK4GSSyOSWZV=m+ed...@mail.gmail.com>
> Content-Type: text/plain; charset="utf-8"
> 
> Hi all
> What is the Bleu Score ?
> How it is calculated on our corpus ?
> Please explain in details.
> 
> Regards,
> 
> 
> 
> *Kalyanee Kanchan Baruah*
> Institute of Science and Technology,
> Gauhati University,Guwahati,India
> Phone- +91-9706242124
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: 
> http://mailman.mit.edu/mailman/private/moses-support/attachments/20140423/7b16830f/attachment.htm
> 
> ------------------------------

_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to