Research Area:  Machine Learning
The rapid growth in the text available on the Internet in the variety of forms demands in-depth research for summarizing text automatically. The summarized form produced from one or multiple documents conveys the important message, which is significantly shorter than the original text. At the same time, summarizing the massive text collection exhibits several challenges. Besides the time complexity, the semantic similarity degree is one of the major issues in text summarization. The summarized text helps the user understand the large corpus much faster and with ease. In this paper, we reviewed several categories of text summarization. First, the techniques have been studied under the category of extractive and abstractive text summarization. Then, a review has been extended for text summarization using topic models. Furthermore, we incorporated machine learning aspects to summarize the large text. We also presented a comparison of techniques over numerous performance measures.
Keywords:  
Author(s) Name:  Rishi Kotadiya, Shivangi Bhatt & Uttam Chauhan
Journal name:  
Conferrence name:   Proceedings of First International Conference on Computing, Communications, and Cyber-Security (IC4S 2019)
Publisher name:  Springer
DOI:  10.1007/978-981-15-3369-3_35
Volume Information:   pp 457–469
Paper Link:   https://link.springer.com/chapter/10.1007/978-981-15-3369-3_35