Selection Informative Units for Extractive Summarization

Author:

Turan Meti̇n1

Affiliation:

1. Computer Engineering Department, İstanbul Ticaret University, Küçükyalı, İstanbul, TURKEY

Abstract

An Extractive Multi-Document Summarizer must select the most informative units and prevents duplication in extraction. In order to achieve this goal, a new technique, called “comprising at least one Representative Term at the Highest Frequency”, called RTHF, is proposed in this work. The units which include representative terms, but with low frequencies are not considered for extraction (selection of the most informative units). On the other hand, these units which provide RTHF feature, precede other similar units in ranking (prevents duplication). The heuristic behind the RTHF is explained by probability. RTHF was experimented on a previously developed and tested paragraph- based Extractive Multi-Document Summarizer. The results show that it enhances the original system by 0.8% ~ 3.2% (Average-F values of ROUGE metrics).

Publisher

World Scientific and Engineering Academy and Society (WSEAS)

Subject

Computer Science Applications,Control and Systems Engineering

Reference23 articles.

1. Kumar YJ, Salim N. Automatic multi document summarization approaches. J Computer Sci 2012; 8: 133-140.

2. Sizov G. Extraction-based automatic summarization - theoretical and empirical investigation of summarization techniques. MSc, Norwegian University, Norwegian, Oslo, 2010.

3. Nenkova A, McKeown K. A survey of text summarization techniques. In: Aggarwal CC, Zhai C-X, editors. Mining Text Data, USA: Springer US, 2012. pp. 43-76.

4. Das D, Martins AFT. A survey on automatic text summarization. 2007; Language Technologies Institute, Technical Report.

5. Mitra M, Singhal A, Buckley C. Automatic text summarization by paragraph extraction. In: Workshop on Intelligent Scalable Text Summarization; 11 July 1997, Madrid, Spain. pp. 39-46.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3