Hybrid Approach for Handling OOV Words

Language transliteration is one of the important area in natural language processing. Accurate transliteration of named entities plays an important role in the performance of machine translation (MT),cross-language information retrieval (CLIR) and question answering (QA), and bilingual lexicon construction. Handling out of vocabulary words is crucial in CLIR and MT. It is important for Machine Translation, especially when the languages do not use the same scripts. This paper addresses the issue of transliteration from Roman Script to Gurmukhi Script. Statistical Approach guided by rules is used for transliteration from English to Punjabi using MOSES, a statistical machine translation tool. The overall TAR after the application of observed rules comes out to be 74.18%.