Design and development of a concept-based multi-document summarization system for research abstracts

2.50
Hdl Handle:
http://hdl.handle.net/2436/27899
Title:
Design and development of a concept-based multi-document summarization system for research abstracts
Authors:
Ou, Shiyan; Khoo, Christopher S.G.; Goh, Dion H.
Abstract:
This paper describes a new concept-based multi-document summarization system that employs discourse parsing, information extraction and information integration. Dissertation abstracts in the field of sociology were selected as sample documents for this study. The summarization process includes four major steps — (1) parsing dissertation abstracts into five standard sections; (2) extracting research concepts (often operationalized as research variables) and their relationships, the research methods used and the contextual relations from specific sections of the text; (3) integrating similar concepts and relationships across different abstracts; and (4) combining and organizing the different kinds of information using a variable-based framework, and presenting them in an interactive web-based interface. The accuracy of each summarization step was evaluated by comparing the system-generated output against human coding. The user evaluation carried out in the study indicated that the majority of subjects (70%) preferred the concept-based summaries generated using the system to the sentence-based summaries generated using traditional sentence extraction techniques.
Citation:
Journal of Information Science, 34 (3): 308-326
Publisher:
Sage
Journal:
Journal of Information Science
Issue Date:
2008
URI:
http://hdl.handle.net/2436/27899
DOI:
10.1177/0165551507084630
Additional Links:
http://jis.sagepub.com/cgi/content/abstract/34/3/308
Type:
Article
Language:
en
ISSN:
01655515; 00000000
Appears in Collections:
Computational Linguistics Group; Computational Linguistics Group

Full metadata record

DC FieldValue Language
dc.contributor.authorOu, Shiyan-
dc.contributor.authorKhoo, Christopher S.G.-
dc.contributor.authorGoh, Dion H.-
dc.date.accessioned2008-05-23T16:31:20Z-
dc.date.available2008-05-23T16:31:20Z-
dc.date.issued2008-
dc.identifier.citationJournal of Information Science, 34 (3): 308-326en
dc.identifier.issn01655515-
dc.identifier.issn00000000-
dc.identifier.doi10.1177/0165551507084630-
dc.identifier.urihttp://hdl.handle.net/2436/27899-
dc.description.abstractThis paper describes a new concept-based multi-document summarization system that employs discourse parsing, information extraction and information integration. Dissertation abstracts in the field of sociology were selected as sample documents for this study. The summarization process includes four major steps — (1) parsing dissertation abstracts into five standard sections; (2) extracting research concepts (often operationalized as research variables) and their relationships, the research methods used and the contextual relations from specific sections of the text; (3) integrating similar concepts and relationships across different abstracts; and (4) combining and organizing the different kinds of information using a variable-based framework, and presenting them in an interactive web-based interface. The accuracy of each summarization step was evaluated by comparing the system-generated output against human coding. The user evaluation carried out in the study indicated that the majority of subjects (70%) preferred the concept-based summaries generated using the system to the sentence-based summaries generated using traditional sentence extraction techniques.en
dc.language.isoenen
dc.publisherSageen
dc.relation.urlhttp://jis.sagepub.com/cgi/content/abstract/34/3/308en
dc.subjectDiscourse parsingen
dc.subjectInformation extractionen
dc.subjectInformation integrationen
dc.subjectMulti-document summarizationen
dc.titleDesign and development of a concept-based multi-document summarization system for research abstractsen
dc.typeArticleen
dc.identifier.journalJournal of Information Scienceen
All Items in WIRE are protected by copyright, with all rights reserved, unless otherwise indicated.