2012/1/6 JAGANADH G <[email protected]>: > @karthik > You can use the Tamil Wikipedia dump as a corpus. Try it
IMHO building a language model out of Tamil Wikipedia is a bad idea.. It has lots of colloquial terms and modern/mixed words.. And sentences are similar to everyday conversations. -- Y _______________________________________________ ILUGC Mailing List: http://www.ae.iitm.ac.in/mailman/listinfo/ilugc
