నైరూప్య

CORPUS ALIGNMENT FOR WORD SENSE DISAMBIGUATION

Shweta Vikram

Machine translation convert one language to another language. Anusaaraka is a machine translation, which is an English to Indian language accessing software. Anusaaraka is a Natural Language Processing (NLP) Research and Development project undertaken by Chinmaya International Foundation (CIF). When any machine do that work they need big parallel corpus that can help for making some rules and disambiguate many senses. It is following hybrid approach but we are working on rule based approach. For this approach we needed big parallel aligned corpus. In this paper we discuss how we collect parallel corpus with the help of some shell scripts, some programs, some tool kit and other things.