Hi, you have to convert your parallel text files yourself into the format that Moses expects, i.e., two files, one for English, one for Hindi, where line x in the English file corresponds to line x in the Hindi file.
If this is rather raw data, you may have to run sentence alignment on your data, using tools such as Hunalign. http://mokk.bme.hu/en/resources/hunalign/ -phi On Wed, Nov 11, 2015 at 5:18 AM, Sunayana Gawde <[email protected]> wrote: > Hello all, > I have developed a Baseline Machine Translation system as stated on moses > website. Also i developed a MT system for a English-Hindi parallel corpus > available online with which i am getting very low BLEU score i.e.5.31. Now > i have a parallel text in English and Hindi in health n tourism corpus > which contains many text files. How to train the system with multiple text > files? I am only familiar to develop that baseline system. Is there > something else which i need specifically for Hindi? > Please help. Thanks. > > -- > *Thanks & Regards* > > Ms. Sunayana R. Gawde. > > DCST, Goa University. > * P**leas**e don't print t**his e-mail unles**s you really need to.* > > _______________________________________________ > 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
