An Adroit Approach for Extractive Text Summarization
Tulasi Prasad Sariki1, G. Bharadwaja Kumar2, Utkarsh Shukla3, Ayush Mishra4
1Tulasi Prasad Sariki, SCSE, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
2G. Bharadwaja Kumar, SCSE, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
3Utkarsh Shukla, SCSE, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
4Ayush Mishra, SCSE, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 2047-2051 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7903068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Over recent years, there has been growing amount of textual data on the World Wide Web. Hence, there is an increasing need for condensing the humungous text information while retaining its content and complete meaning. Text Summarization is the process of shortening the source text into a more concise form without losing the essence of the original text. Out of the two fundamental approaches i.e. abstractive and extractive, extractive summarization is the predominant approach in literature which fetches the significant sentences by using statistical and linguistic characteristics. In this paper, a judicious framework for extractive text summarization has been presented. The proposed approach contains three different concurrent pipelines to improve the effectiveness of the Summarization process. The proposed framework combines Statistical, NER-based and CUE-phrase methods in an effectual way to extract the summary. The novelty in our approach is to use semantic distance between the sentences to remove the redundant sentences in the final phase. The experimental results show that the proposed framework surpassed the ROUGE-L scores given by state-of-art summarization techniques.
Keywords: Text Summarization, Extractive Summary Sentence Scoring, Statistical Analysis, Semantic Analysis.
Scope of the Article: Text Mining