Home / Current Issue / Paper 1702654
Auto Text Summarization
Subject area: Science,Engineering and Technology · Area of research: DATA PROCESSING
Abstract
Automatic text summarization is basically summarizing of the given paragraph using natural language processing and machine learning. There has been an explosion in the amount of text data from a variety of sources. This volume of text is an invaluable source of information and knowledge which needs to be effectively y summarized to be useful. In this review, the main approaches to automatic text hello. We review the different processes for summarization and describe the effectivenessand shortcomings of the different methods.Two types will be used i.e.-extractive approach and abstractive approach. Thebasic idea behind summarization is finding the subset of the data which contains the information of all the set. There is a great need to reduce unnecessary data. It is very difficult to summarize the document manually so there is the great need of automatic method. The extractive approach basically chooses the various and unique sentences, sections and so forth make a shorter type of the first report. The sentences are estimated and chosen based on accurate highlights of the sentences. In the Extractive technique, we have to choose the subset from the given expression or sentences in given frame of the synopsis.
Keywords
Auto Text; Extractive; Summarization
References
[1] Jing, Hongyan. “Sentence Reduction for Automatic Text Summarization.” Proceedings of the Sixth Conference on Applied Natural Language Processing -, 2000,
[2] Garg, Sneh, and Sunil Chhillar. “Review of Text Reduction Algorithms and Text Reduction Using Sentence Vectorization.” International Journal of Computer Applications, vol. 107, no. 12, 2014, pp. 39–42.,
[3] JRC1995. “ JRC1995/Abstractive- Summarization.” GitHub, github.com/JRC1995/Abstractive- Summarization/blob/master/Summarization_mo del.ipynb.
[4] “A Gentle Introduction to Text Summarization.” Machine Learning Mastery, 21 Nov. 2017, machinelearningmastery.com/gentle- introduction-text-summarization/.
[5] “A Survey of Relevant Text Content Summarization Techniques.” International Journal of Science and Research (IJSR), vol. 5, no. 1, 2016, pp. 129–132.,
[6] “Text Summarization in Python: Extractive vs. Abstractive Techniques Revisited.” Pragmatic Machine Learning, rare-technologies.com/text- summarization-in-python-extractive-vs- abstractive-techniques-revisited/.
[7] “Text Summarization with TensorFlow.” Google AI Blog, 24 Aug. 2016, ai.googleblog.com/2016/08/text-summarization- with-tensorflow.html.
[8] “Encoder-Decoder Long Short-Term Memory Networks.” Machine Learning Mastery, 20 July 2017, machinelearningmastery.com/encoder- decoder-long-short-term-memory-networks/.
How to cite this paper
@article{1702654,
author = {Aditya Kirtane, Akhil Pawar, Suhas Tambe, Prof. M. R. Gorbal},
title = {Auto Text Summarization},
journal = {Iconic Research And Engineering Journals},
year = {2021},
volume = {4},
number = {10},
pages = {76-83},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1702654.pdf},
abstract = {Automatic text summarization is basically summarizing of the given paragraph using natural language processing and machine learning. There has been an explosion in the amount of text data from a variety of sources. This volume of text is an invaluable source of information and knowledge which needs to be effectively y summarized to be useful. In this review, the main approaches to automatic text hello. We review the different processes for summarization and describe the effectivenessand shortcomings of the different methods.Two types will be used i.e.-extractive approach and abstractive approach. Thebasic idea behind summarization is finding the subset of the data which contains the information of all the set. There is a great need to reduce unnecessary data. It is very difficult to summarize the document manually so there is the great need of automatic method. The extractive approach basically chooses the various and unique sentences, sections and so forth make a shorter type of the first report. The sentences are estimated and chosen based on accurate highlights of the sentences. In the Extractive technique, we have to choose the subset from the given expression or sentences in given frame of the synopsis.},
keywords = {Auto Text; Extractive; Summarization},
month = {April},
}