NLP BASED TEXT SUMMARIZATION USING BART MODEL
Ms. Sangavi N1, Ms. Umamaheswari M2, Ms. Subasri V3
1Assistant Professor Level – I, Computer Science and Engineering & Bannari Amman Institute of Technology
2 UG Scholar, Electrical and Electronics Engineering & Bannari Amman Institute of Technology
3 UG Scholar, Computer Science and Engineering & Bannari Amman Institute of Technology
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Text summarization plays a major role which can be used to summarize articles, papers, documents, etc. It greatly helps the students, business executives, librarian, teachers and many people in different profiles to quickly get the gist of research papers, latest news, trends in industry, summarize books, articles, etc. Summarizing provides a concise overview of a document which helps us to make better decisions and communicate information more effectively. In this project we are going to implement an nlp based text summarization using bart model and finally deployed using django framework. Bart hugging face transformer model is one of the nlp models. Its input and output are in the form of sequence. The high-dimensional representation of the input is learnt by the encoder and then mapped to the decoder. The bart model is first pre-trained on a big text (like book corpus or wikipedia). Pretraining ensures that the model "understands the language" and has a solid foundation from which to learn and how to carry out further tasks. Since it will determine how successfully the model can be trained for tasks like text classification or text summarization, the model's capacity to understand language is more effective. The pre-trained weights and weights in the bart model are fine-tuned on question answering, text summarization, sequence classification, etc. Therefore, using bart model we can able to generate text in both extractive and abstractive way, by which we can get the simpler summarization with the important sentences and also more fluent and accurate summarization by understanding the meaning of the text. Finally, to provide a user-friendly interface, by which the users can easily use the text summarization, the project will be deployed using django framework. It allows us to easily build web applications.
Key Words: BART, NLP, summarization, Wikipedia, pretrained