Multi-document summarization focusing on extracting and integrating similarities and differences among documents

Shiyan Ou, Christopher S.G. Khoo, Dion H. Goh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The study was to develop a method for automatic summarization of sets of related research abstracts. This summarization method focused on extracting and integrating similarities and differences among different abstracts. In the research studies which aim to look for relationships between research concepts, similarities and differences are mainly reflected through research concepts and relationships expressed in the text. Thus the summarization method extracts research concepts and relationships from each research abstract, integrates similar concepts and relationships across different abstracts, and incorporates them into new sentences to produce a summary. This paper reports the three main summarization steps - discourse parsing, concept extraction and integration, and relationship extraction and integration. Each step was evaluated by comparing the machine output against human codings.

Original languageEnglish
Title of host publicationInternational Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings
EditorsGalia Angelova, Kalina Bontcheva, Ruslan Mitkov, Nicolas Nicolov, Nikolai Nikolov
PublisherAssociation for Computational Linguistics (ACL)
Pages442-446
Number of pages5
ISBN (Electronic)9789549174373
Publication statusPublished - 2007
Externally publishedYes
EventInternational Conference Recent Advances in Natural Language Processing, RANLP 2007 - Borovets, Bulgaria
Duration: Sept 27 2007Sept 29 2007

Publication series

NameInternational Conference Recent Advances in Natural Language Processing, RANLP
Volume2007-January
ISSN (Print)1313-8502

Conference

ConferenceInternational Conference Recent Advances in Natural Language Processing, RANLP 2007
Country/TerritoryBulgaria
CityBorovets
Period9/27/079/29/07

ASJC Scopus Subject Areas

  • Software
  • Computer Science Applications
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Keywords

  • Automatic text summarization
  • Concept clustering
  • Concept extraction
  • Relationship extraction
  • Relationship integration

Fingerprint

Dive into the research topics of 'Multi-document summarization focusing on extracting and integrating similarities and differences among documents'. Together they form a unique fingerprint.

Cite this