Sanskrit Tag-sets and Part-Of-Speech Tagging Methods - A survey

Paper Topic :

Artificial Intelligence

Author Name :

Sulabh Bhatt

Abstract :

This paper presents some great features of Sanskrit- one of the oldest language of the world from Natural Language Processing (NLP) perspective. Part Of Speech (POS) tagging is the most initial step for developing any NLP application. POS tagger assigns a tag like noun, verb, pronoun, adjective or other category that best suits to the word and also the context of the sentence to which it belongs. Moreover, this paper also provides brief introduction to various approaches and the working of two most famous statistical methods used for POS tagging: Hidden Markov Model (HMM) and Conditional Random Fields (CRF).

Download Article