Automatic Text Summarization – A Review

Authors

  • Behjat Reyaz
  • Falak Jan
  • Riyaz ul Haque

Abstract

ABSTRACT

 

We present Encoder/Decoder a unique methodology for summarization of text documents. The summarization of text is to be done in two forms one is abstractive and the other one is extractive. Summarization of text is a main job of natural language processing. With the help of new idea we make a unique amalgam model of abstractive-extractive to combine BERT(Bidirectional Encoder Representations from Transformers). Firstly we transform the summaries which are abstractive to their respective embeddings using BERT. Secondly, pre-train two models separately by implementing BERT pre-trained model. Then the extraction network and abstraction network are combined to form a unified model by reinforcement learning. As we know that Automatic text summarization fundamentally compress a long document into a shorter format while securing its intelligence content and overall meaning .A number of automatic summarizers exist which is able of producing good content summaries, but they do not focus on securing the underlying meaning and semantics of the text. So we also catch and preserve the semantics of text as the fundamental feature for summarizing a document using Distribution Semantic model. Also Clustering and Ranking of sentences is done by using various algorithms. In this paper Automatic text summarization is performed on single documents and is generic based. We evaluate our summarizer with the help of ROUGE(Recall-Oriented Understudy for Gisting Evaluation)on DUC-2007 dataset and compare with other state-of-the-art summarizers.

 

Keywords: Encoder, Decoder, BERT, Summarizers, ROUGE

 

E-mail:[email protected]

 

 

Downloads

Published

2020-12-29

Issue

Vol. 7 No. 3 (2020)

Section

Review Articles

License

Declaration and Copyright Transfer Form

(to be completed by authors)

I/ We, the undersigned author(s) of the submitted manuscript, hereby declare, that the above manuscript which is submitted for publication in the STM Journals(s), is not published already in part or whole (except in the form of abstract) in any journal or magazine for private or public circulation, and, is not under consideration of publication elsewhere.

  • I/We will not withdraw the manuscript after 1 week of submission as I have read the Author Guidelines and will adhere to the guidelines.
  • I/We Author(s ) have niether given nor will give this manuscript elsewhere for publishing after submitting in STM Journal(s).
  • I/ We have read the original version of the manuscript and am/ are responsible for the thought contents embodied in it. The work dealt in the manuscript is my/ our own, and my/ our individual contribution to this work is significant enough to qualify for authorship.
  •  I/We also agree to the authorship of the article in the following order:

Author’s name                                    

 

1. ________________

2. ________________

3. ________________

4. ________________

 

We  Author(s) tick this box and would request you to consider it as our signature as we agree to the terms of this Copyright Notice, which will apply to this submission if and when it is published by this journal.