Improved Unsupervised Framework for Solving Synonym, Homonym, Hyponymy & Polysemy Problems from Extracted Keywords and Identify Topics in Meeting Transcripts

Abstract

Keyword is the important item in a document that provides efficient access to the content of adocument. In the Existing system, Synonym, Homonym, Hyponymy and Polysemy problemswere solved from only trained extracted keywords in the meeting transcripts. Synonym problem means different wordswhich have similar meaning they are grouped and single keyword is extracted . Hyponymy problem means one word denoting subclassthat is considered and super class keyword is extracted. Homonymmeans a word which can have two or more different meanings.. APolysemy means word with different, but related senses. Hidden topics from meeting transcripts can be found using LDA model. MaxEnt classifier is used for extracting keywords and topics which will be used for information retrievalTraining the keyword from the dataset is separately needed for all the problems, it is not an automatic one .In this proposed frame work, a dataset has been designed tosolve the above mentioned four problems automatically.