It's usually BLEU-4. I'm not sure what you mean by Smoothed BLEU.

I don't think there's a standard BLEU score, even the original BLEU scoring script is continuously updated:

https://github.com/moses-smt/mosesdecoder/blob/master/scripts/generic/mteval-v*.pl

Each version may give a slightly different answer. So when you quote a BLEU score, you should say exactly what version you used


On 09/04/2017 04:26, Tran Anh wrote:
Dear all,

I want to ask about using BLEU to calculate the similarity between two sentences (the same language). I trained the translation model using MOSES. Then input two files with the same number of line, one sentence per line. I get the result that every pair of sentences has the corresponding BLEU score. So, I want to ask: BLEU in Moses that I used to calculate the similarity is common BLEU-4 or Smoothed BLEU?

Thank you so much!
Anh,


On Sun, Mar 19, 2017 at 12:00 AM, <[email protected] <mailto:[email protected]>> wrote:

    Send Moses-support mailing list submissions to
    [email protected] <mailto:[email protected]>

    To subscribe or unsubscribe via the World Wide Web, visit
    http://mailman.mit.edu/mailman/listinfo/moses-support
    <http://mailman.mit.edu/mailman/listinfo/moses-support>
    or, via email, send a message with subject or body 'help' to
    [email protected] <mailto:[email protected]>

    You can reach the person managing the list at
    [email protected] <mailto:[email protected]>

    When replying, please edit your Subject line so it is more specific
    than "Re: Contents of Moses-support digest..."


    Today's Topics:

       1. Re: Moses compiling error with boost 1.55 (Gongbo Tang)


    ----------------------------------------------------------------------

    Message: 1
    Date: Fri, 17 Mar 2017 21:24:56 +0000
    From: Gongbo Tang <[email protected]
    <mailto:[email protected]>>
    Subject: Re: [Moses-support] Moses compiling error with boost 1.55
    To: Raj Dabre <[email protected] <mailto:[email protected]>>
    Cc: "[email protected] <mailto:[email protected]>"
    <[email protected] <mailto:[email protected]>>
    Message-ID:
<[email protected]
    <mailto:[email protected]>>
    Content-Type: text/plain; charset="iso-8859-1"

    Yes, I also think that there is something wrong with the Boost
    version, or gcc version.

    There is still an error when I compile with absolute path.

    Thank you very much!

    Best,
    Gongbo
    ________________________________
    From: Raj Dabre [[email protected] <mailto:[email protected]>]
    Sent: Friday, March 17, 2017 4:02 PM
    To: Gongbo Tang
    Cc: Hieu Hoang; [email protected] <mailto:[email protected]>
    Subject: Re: [Moses-support] Moses compiling error with boost 1.55

    Use the latest boost (1.63 I think) and it should work. I had the
    same issue.

    On Fri, Mar 17, 2017 at 11:48 PM, Hieu Hoang <[email protected]
    <mailto:[email protected]><mailto:[email protected]
    <mailto:[email protected]>>> wrote:
    there's a lot of errors due to unit tests not compiling properly.
    I'm not sure why this happens, but you can ignore it.

    However, there's failure due to not linking with irstlm correctly.
    This may be because the path to irstlm is incorrect, it must also
    be absolute path, not relative

    * Looking for MT/NLP opportunities *
    Hieu Hoang
    http://moses-smt.org/


    On 17 March 2017 at 14:13, Gongbo Tang <[email protected]
    <mailto:[email protected]><mailto:[email protected]
    <mailto:[email protected]>>> wrote:
    Hi,

    I encountered an error when I was running the command:

    bjam -j4 --with-giza=/the-dir-of-giza-pp
    --with-irstlm=opt/irstlm-5.80.08/ >& bjam.log

    The log is attached.

    And, the gcc version is 4.8.2; the Boost version is 1.55. The
    server system is Red Hat 4.4.7-17.

    Best,
    Gongbo

    _______________________________________________
    Moses-support mailing list
    [email protected]
    <mailto:[email protected]><mailto:[email protected]
    <mailto:[email protected]>>
    http://mailman.mit.edu/mailman/listinfo/moses-support
    <http://mailman.mit.edu/mailman/listinfo/moses-support>



    _______________________________________________
    Moses-support mailing list
    [email protected]
    <mailto:[email protected]><mailto:[email protected]
    <mailto:[email protected]>>
    http://mailman.mit.edu/mailman/listinfo/moses-support
    <http://mailman.mit.edu/mailman/listinfo/moses-support>




    --
    Raj Dabre.
    Doctoral Student,
    Graduate School of Informatics,
    Kyoto University.
    CSE MTech, IITB., 2011-2014

    -------------- next part --------------
    An HTML attachment was scrubbed...
    URL:
    
http://mailman.mit.edu/mailman/private/moses-support/attachments/20170317/62c08583/attachment-0001.html
    
<http://mailman.mit.edu/mailman/private/moses-support/attachments/20170317/62c08583/attachment-0001.html>

    ------------------------------

    _______________________________________________
    Moses-support mailing list
    [email protected] <mailto:[email protected]>
    http://mailman.mit.edu/mailman/listinfo/moses-support
    <http://mailman.mit.edu/mailman/listinfo/moses-support>


    End of Moses-support Digest, Vol 125, Issue 39
    **********************************************




_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

--
Hieu Hoang
http://moses-smt.org/

_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to