GUI Application for Summarizing and Optimizing Audio and Textual Data

Abstract

Text summarization is one of those implementations of nlp which have been popularized greatly over time. Earlier versions were simple and sometimes were based on only one basis. nowadays summarization can broadly be divided into two main categories to classify it. They are abstract and extractive summarizers. the implementation of seq2seq model for summarization of textual data using tensor flow/ keras and demonstrated on amazon or social response reviews, issues and news articles. Text summarization basically works by cutting out the excess data and giving only the required data. LSTM summarization which we used in this project of ours trains the machine to make meaningful sentences based on the dataset given. So, our aim is to compare spacy, gensim and nltk summarization technique by the input requirements and try to prove that the implemented LSTM based summariser is more efficient and better.