Hi all I am trying to develop a specific segmenter. The goal is to send Moses decoder sentences instead of large textual flows syntactically incoherent. In order to integrate this segmenter in an automatic workflow of documents translation. I would define as a sentence delimiter any character that the decoder does not take into account in its statistics.
Is there a completely neutral character (I don't want it to be considered unknown) that I could use as a delimiter? Thank you for your help Arnaud Gicquel -- Lingua Custodia 1, Place Charles de Gaulle 78180 Montigny le Bretonneux - France Tel : 33 1 30 44 04 23 Email : arnaud.gicq...@linguacustodia.com Website : www.linguacustodia.com
_______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support