Tamil-English Cross Lingual Information Translation and Retrieval in Agricultural Domain using VSM

Computer Engineering

Language processing is prompt research area across the country. In that, query translation is one of the major areas of research for the past ten decades. Tamil is morphologically rich and complex language. The suitable morphological processing is very important for Cross Lingual Information Retrieval (CLIR). The contributions towards Tamil to English query translation and transliteration are limited when comparing to other language even though the Tamil language is the official language in south India, Sri Lanka, and Singapore. We propose a CLIR system in agriculture domain for the farmers of Tamil Nadu which helps them to state their query in Tamil and retrieve the documents in English. It uses a bilingual dictionary for translating the user queries and n-gram based approach are used to recover the problem of Word Sense Disambiguation (WSD). The named entities (or) out of vocabulary words are transliterated with the help of statistical system. The retrieved documents are ranked with the help of Vector space model.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.