A BRIEF STUDY ON HINDI TEXT SUMMARIZATION USING NATURAL LANGUAGE PROCESSING









Abstract

The goal of text summarization is to create a summary of the input document that includes important sentences as well as all pertinent information. It removes the unnecessary, insignificant content and provides you with vital information in a compressed format that is usually half the length of the original Input text document. In our approach, we employed the extractive summarization method. The purpose of this strategy is to choose essential sentences from the original input text document and concatenate them into a shorter version. We use numerical approaches to extract the summary in our suggested system, which has the advantage of not requiring any prior data for summary extraction. The most essential sentences that must be included in the summary are determined based on the score of Numerical Features of sentences such as TF-ISF, length of the sentences, the position of the phrases, similarities between the sentences, and Numerical data. Sentences will be chosen based on the score earned by the sentences based on the above-mentioned characteristics. The higher the sentence's score, the more likely it is that the sentence will be included in the summary. The score is determined by extracting features from each sentence in a text document. We have chosen Hindi as the study language for our planned project.


Modules


Algorithms


Software And Hardware