Text Document Summarization Using POS tagging for Kannada Text Documents

Humongous amount of data available on the world wide web has been a constant issue pertaining to better Information Retrieval (IR) techniques. Text document summarization is there around for the past several decades, but providing a succinct summary has been challenging as ever. This work focuses on extractive summarization techniques using POS tagging, where the goal is to tag individual words with its parts of speech in a document and do the extractive summarization with more grammatical meaning. The Hidden Markov Model (HMM) is used for tagging the dataset. The idea is to use sentence ranking to produce the summary of a given document. This method of summarization uses the key phrase extraction, where the goal is to select individual words or sentences to tag a document to create text document summary.