[Corpora-List] extract sentences from search graph file (MOSES)

[Philipp Koehn]

Hi,

if you are talking about extracting _all_ translations from the search
graph, then there is no tool for it, and the number of all possible
translations is typically too large to be printed in any reasonable way.

If you are looking for the best translation, you should follow the
forward states, starting with hypothesis 0.

-phi



On Sat, Aug 9, 2014 at 7:58 AM, Saeed Farzi <saeedfarzi at gmail.com> wrote:

>  Dear all,
>
> I am trying to extract all translated sentences form output search
> graph file generated by option -output-search-graph-extended. i wonder
> if anybody give me a code or tool that do this for me?
> tnx in advance,
> --
>            S.Farzi, Ph.D. Student
>     Natural Language Processing Lab,
>   School of Electrical and Computer Eng.,
>                Tehran University
>              Tel: +9821-6111-9719
>
> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20140811/7403f4f5/attachment.htm>
-------------- next part --------------
_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora