Dear Mr.Nicola
cc Moses expert supporter

I have same question with Mr.Feth Bougares but about word lattice
decoding. I am working on Vietnamese to Japanese Statistical machine
Translation. As you know there is not vietnamese-japanese paralell data,
so I make english word lattices from vietnamese japanese dictionary.
After that use english - japanese SMT to translate.
The problem are make word lattice format. In my test data, has a part of
tested data weren't success. And the Segementation Faul is throwed.

Adn my question are
 - how moses decode a word lattices?
 - waht is the means of "probability associated with an edge", are these
true probability ? or there is any method to calculate them.
 - how moses use word lattices scores (above probabilities)? and how it
make choice between path inside the word lattices ?
 - what is the means of -weight-i added to configure file moses.ini
can you explain that please ?

Thanks.
Manh Hung (Toyohashi Un.Japan)

> between path inside the cn ?
2009-05-12 (火) の 15:53 +0200 に Nicola Bertoldi さんは書きました:
> I am answering him privately.
> 
> Nicola
> 
> 
> On 5/12/09 3:26 PM, "Fethi Bougares" <fethi.bouga...@imag.fr> wrote:
> 
> Hello,
> 
>  I am Working on  Arabic To English Statistical Machine Translation.
>  AS you now Arabic is a rich morphological language.
>  So i use confusion network (as input type) to combine
>  many possible morphologique analyses of arabic text.
> 
>  CN decoding is not well documented in moses web site. So i need some
> explanation
>  My questions are  :
> 
>   - how moses decode a confusion network ?
>   - the means of the word posterior parameters added to configuration
> file 'moses.ini' ?
>   - how moses use confusion network scores ? and how it make choice
> between path inside the cn ?
>   - the effect of cn tuning.
>   - finally i try to change the scores, giving zero to a path but moses
> -when it decode my cn- it take this path ( even it has an edge with zero
> score)
>       can you explain that please ?
>   Thanks.
>   Bougares. LIG Laboratory (Grenoble French)
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
> 
> 
> 
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
> 

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

Reply via email to