Gazetteer Preparation for Named Entity Recognition in Indian Languages
Sujan Kumar Saha, Sudeshna Sarkar, Pabitra Mitra · International Joint Conference on Natural Language Processing · 2008
This paper describes our approaches for the preparation of gazetteers for named entity recognition (NER) in Indian languages. We have described two methodologies for the preparation of gazetteers 1 . Since the relevant gazetteer lists are more easily available in English we have used a transliteration based approach to convert available English name lists to Indian languages. The second approach is a context pattern induction based domain specific gazetteer preparation. This approach uses a domain specific raw corpus and a few seed entities to learn context patterns and then the corresponding name lists are generated by using bootstrapping.