Hi, I would suggest to skip the word alignment step and create a file that has diagonal alignment links for each sentence (1-1,2-2,3-3,...).
-phi On 7 Aug 2010 19:57, "Thanh-Le Nguyen" <[email protected]> wrote: Hello everybody, we are working on a project with a fictive source and target languages. In our case the source and target sentences are constrained to have the same word order. I.e. each word in the sentence of the target language corresponds to a translation of the word in the sentence of the source language with the same position. E.g. the third word in the target sentence is a translation of the third word in the source sentence. Therefore, for creating the phrase table no alignment information or reordering is needed. Is there a way to set up Moses for extracting the phrase table without using the information about alignment and reordering? Thanks, Le _______________________________________________ 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
