Hi,

the scoring tool in MERT relies on the provided tokenization, while
mteval-v13.pl does its own tokenization. That may explain the difference.

-phi

2011/10/4 Prasanth K <[email protected]>:
> Hi all,
>
> I have tried using this evaluator that Matous is talking about.
> The problem is that there is a difference of 0.5-1 BLEU points difference in
> the value given by the evaluator script and the regular mteval-v13.pl
> script.
> Certainly not a case of precision error!
>
> I am evaluating the tokenized lowercase outputs and reference translations,
> and the difference was observed for more than 15-20 experiments. So not a
> case of random error either.
>
> Any suggestions about what I could possibly doing wrong?
>
> - Prasanth
>
>
> 2011/9/26 Matouš Macháček <[email protected]>
>>
>> Hi,
>>
>> There is a tool for calculating metric score for given candidate and
>> reference file. You can find this tool in Moses repository under the
>> mert directory. It uses the same metrics as mert so you can use:
>>
>> evaluator --sctype TER --reference ref.file --candidate cand.file
>>
>> usage: evaluator [options] --reference ref1[,ref2[,ref3...]]
>> --candidate cand1[,cand2[,cand3...]]
>> [--sctype|-s] the scorer type (default BLEU)
>> [--scconfig|-c] configuration string passed to scorer
>>        This is of the form NAME1:VAL1,NAME2:VAL2 etc
>> [--reference|-R] comma separated list of reference files
>> [--candidate|-C] comma separated list of candidate files
>> [--bootstrap|-b] number of booststraped samples (default 0 - no
>> bootstraping)
>> [--rseed|-r] the random seed for bootstraping (defaults to system clock)
>> [--help|-h] print this message and exit
>>
>> Matous Machacek
>>
>> 2011/9/26 saeed farzi <[email protected]>:
>> > Hi all,
>> >
>> > Can anybody introduce me a tool for calculating TER, and a tool for
>> > analysizing ouput of moses.
>> > --
>> >           S.Farzi, Ph.D. Student
>> >    Natural Language Processing lab,
>> >  School of Electrical and Computer Eng,
>> >               Tehran University
>> >             Tel: +9821-6111-9719
>> > _______________________________________________
>> > Moses-support mailing list
>> > [email protected]
>> > http://mailman.mit.edu/mailman/listinfo/moses-support
>> >
>>
>> _______________________________________________
>> Moses-support mailing list
>> [email protected]
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
>
> --
> "Theories have four stages of acceptance. i) this is worthless nonsense; ii)
> this is an interesting, but perverse, point of view, iii) this is true, but
> quite unimportant; iv) I always said so."
>
>   --- J.B.S. Haldane
>
> _______________________________________________
> Moses-support mailing list
> [email protected]
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>

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

Reply via email to