Hi, We have recently added a transliteration module in Moses. Here's how to use it:
http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc5 When enabled the model will try to mine transliteration pairs from the word-aligned parallel corpus and build a transliteration model over the resulting transliteration training data. It is totally unsupervised and language independent. You can find more details in this paper. http://aclweb.org/anthology//E/E14/E14-4029.pdf Cheers, Nadir On Sun, Jun 8, 2014 at 8:35 PM, Shahid Khan <[email protected]> wrote: > Hi, > > Is there a module to transliterate OOV words in Moses? Or any standalone > transliteration toolkit to do this? > > I am trying to translate some English data into Hindi. Our system is based > on the data provided for WMT this year and some additional in-domain data. > But the number of OOVs is still massive. However, at least half of these > could be transliterated. > > Regards, > Shahid > > _______________________________________________ > Mt-list site list > [email protected] > http://lists.eamt.org/mailman/listinfo/mt-list >
_______________________________________________ Mt-list site list [email protected] http://lists.eamt.org/mailman/listinfo/mt-list
