Named Entity Recognition and Classification in Kannada Language

Named Entity Recognition and classification (NERC) is an essential and challenging task in (NLP). Kannada is a highly inflectional and agglutinating language providing one of the richest and most challenging sets of linguistic and statistical features resulting in long and complex word forms, which is large in number. It is primarily a suffixing Language and inflected word starts with a root and may have several suffixes added to the right. It is also a Freeword order Language. Like other Indian languages, it is a resource poor language. Annotated corpora, name dictionaries, good morphological analyzers, Parts of Speech (POS) taggers etc. are not yet available in the required measure and not many works are reported for this language. The work related to NERC in Kannada is not yet reported. In recent years, automatic named entity recognition and extraction systems have become one of the popular research areas. Building NERC for Kannada is challenging. It seeks to classify words which represent names in text into predefined categories like person name, location, organization, date, time etc. This paper deals with some attempts in this direction. This work starts with experiments in building Semi-Automated Statistical Machine learning NLP Models based on Noun Taggers. In this paper we have developed an algorithm based on supervised learning techniques that include Hidden Markov Model (HMM). Some sample results are reported.