Paper Title
Unsupervised Methods for Extractive Query-Oriented Text Summarization: A Review

Abstract
In this modern world the user is capable of having easy access to a pool of information through internet by means of Wikipedia, e-books, e-mails, News websites and forums etc. so if a user wants to read and understand the whole text it costs him/her a lot of time. Automatic text summarization is being used as a constructive technique through which a user can understand the whole text in brief by saving his/her crucial time. Text summarization can be done using abstractive and extractive techniques of Natural Language Processing (NLP). Query-oriented text summarization is one of the very effective extractive text summarization technique. In Query-oriented text summarization the summary is generated as an answer to input query, this is done by extracting the most important features from the text which are related to input query. The primary emphasis of this work lies in comparative study of unsupervised machine learning (ML) methods to generate the query-oriented summary of the text. We are going to analyse and interpret the methods to make inferences which will help the scientists and developers foresee the short comes as pre-emptive measures in choosing the most effective method for this text summarization technique. Keywords - Query-Oriented Text Summarization, Extractive Summarization, Machine Learning, Natural Language Processing, Unsupervised Learning.