STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Artificial Intelligence Research & Advances Review Article

Extractive Text Summarization: An Application Based Study

  1. Deepanshu Anand Department of Information Technology, Maharaja Agrasen Institute of Technology
  2. Yugansh Gupta Department of Information Technology, Maharaja Agrasen Institute of Technology
  3. Arnav Sabharwal Department of Information Technology, Maharaja Agrasen Institute of Technology
  4. Vinay Kumar Saini Department of Information Technology, Maharaja Agrasen Institute of Technology
  5. Anshu Khurana Department of Information Technology, Maharaja Agrasen Institute of Technology

Abstract

Text summarization is an essential tool for extracting important information from lengthy texts or documents. Text Summarization has two main methodologies namely: Extractive Summarization and Abstractive Summarization. This study concentrates on extractive summarising, which selects significant sentences straight from the source material to create a summary. It is a popular option for many practical applications since it frequently produces summaries that are more accurate in terms of substance. In abstractive summarization, the summaries are generated by using the words that are not in the original text. However, the disadvantage of the above technique lies in the areas, where we want to retain the original text from the source. Hence the need of extractive summarization arises. Although, there are few drawbacks associated to extractive summarization which include the possibility of repetition and the dependence on pre-existing content. This study investigates how extractive summarization could be used to create end-to-end applications that are broadly applicable across various applications like legal document analysis. Through the resolution of these constraints and the utilisation of advances in natural language processing, extractive summarization could provide beneficial outcomes for a range of applications.

Keywords

References (12)

  1. El-Kassas WS, Salama CR, Rafea AA, Mohamed HK. Automatic text summarization: A comprehensive survey. Expert Syst Appl. 2021; 165: 113679.
  2. Sethi P, Sonawane S, Khanwalker S, Keskar RB. Automatic text summarization of news articles. In 2017 IEEE International Conference on Big Data, IoT and Data Science (BID). 2017 Dec; 23–29.
  3. Kanapala A, Pal S, Pamula R. Text summarization from legal documents: a survey. Artif Intell Rev. 2019; 51(1): 371–402.
  4. Moratanch N, Chitrakala S. A survey on extractive text summarization. In 2017 IEEE international conference on computer, communication and signal processing (ICCCSP). 2017 Jan; 1–6.
  5. Moratanch N, Chitrakala S. A survey on abstractive text summarization. In 2016 IEEE International Conference on Circuit, power and computing technologies (ICCPCT). 2016 Mar; 1–7.
  6. Luhn HP. The Automatic Creation of Literature Abstracts. IBM Journal of Research and Development. 1958;2(2):159-165. doi:10.1147/rd.22.0159
  7. Erkan G, Radev DR. Lexrank: Graph-based lexical centrality as salience in text summarization. J Artif Intell Res. 2004; 22(1): 457–479.
  8. Mihalcea R, Tarau P. Textrank: Bringing order into text. In Proceedings of the 2004 conference on empirical methods in natural language processing. 2004 Jul; 404–411.
  9. Nallapati R, Zhai F, Zhou B. Summarunner: A recurrent neural network-based sequence model for extractive summarization of documents. In Proceedings of the AAAI conference on artificial intelligence. 2017 Feb; 31(1).
  10. Cheng J, Lapata M. Neural summarization by extracting sentences and words. arXiv preprint arXiv:1603.07252. 2016.
  11. Liu Y. Fine-tune BERT for extractive summarization. arXiv preprint arXiv:1903.10318. 2019.
  12. Lin CY. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. Barcelona, Spain: Association for Computational Linguistics; 2004 Jul; 74–81.
Support