Persistent Link:
http://hdl.handle.net/10150/106042
Title:
Automatic multi-document summarization for digital libraries
Author:
Ou, Shiyan; Khoo, Christopher S.G.; Goh, Dion H.
Editors:
Khoo, C.; Singh, D.; Chaudhry, A.S.
Citation:
Automatic multi-document summarization for digital libraries 2006, :72-82
Publisher:
School of Communication & Information, Nanyang Technological University
Issue Date:
2006
URI:
http://hdl.handle.net/10150/106042
Submitted date:
2007-05-22
Abstract:
With the rapid growth of the World Wide Web and online information services, more and more information is available and accessible online. Automatic summarization is an indispensable solution to reduce the information overload problem. Multi-document summarization is useful to provide an overview of a topic and allow users to zoom in for more details on aspects of interest. This paper reports three types of multi-document summaries generated for a set of research abstracts, using different summarization approaches: a sentence-based summary generated by a MEAD summarization system that extracts important sentences using various features, another sentence-based summary generated by extracting research objective sentences, and a variable-based summary focusing on research concepts and relationships. A user evaluation was carried out to compare the three types of summaries. The evaluation results indicated that the majority of users (70%) preferred the variable-based summary, while 55% of the users preferred the research objective summary, and only 25% preferred the MEAD summary.
Type:
Conference Paper
Language:
en
Keywords:
Information Extraction; Digital Libraries; Natural Language Processing
Local subject classification:
digital libraries; multi-document summarization; automatic summarization; abstracting; summarization

Full metadata record

DC FieldValue Language
dc.contributor.authorOu, Shiyanen_US
dc.contributor.authorKhoo, Christopher S.G.en_US
dc.contributor.authorGoh, Dion H.en_US
dc.contributor.editorKhoo, C.en_US
dc.contributor.editorSingh, D.en_US
dc.contributor.editorChaudhry, A.S.en_US
dc.date.accessioned2007-05-22T00:00:01Z-
dc.date.available2010-06-18T23:38:44Z-
dc.date.issued2006en_US
dc.date.submitted2007-05-22en_US
dc.identifier.citationAutomatic multi-document summarization for digital libraries 2006, :72-82en_US
dc.identifier.urihttp://hdl.handle.net/10150/106042-
dc.description.abstractWith the rapid growth of the World Wide Web and online information services, more and more information is available and accessible online. Automatic summarization is an indispensable solution to reduce the information overload problem. Multi-document summarization is useful to provide an overview of a topic and allow users to zoom in for more details on aspects of interest. This paper reports three types of multi-document summaries generated for a set of research abstracts, using different summarization approaches: a sentence-based summary generated by a MEAD summarization system that extracts important sentences using various features, another sentence-based summary generated by extracting research objective sentences, and a variable-based summary focusing on research concepts and relationships. A user evaluation was carried out to compare the three types of summaries. The evaluation results indicated that the majority of users (70%) preferred the variable-based summary, while 55% of the users preferred the research objective summary, and only 25% preferred the MEAD summary.en_US
dc.format.mimetypeapplication/pdfen_US
dc.language.isoenen_US
dc.publisherSchool of Communication & Information, Nanyang Technological Universityen_US
dc.subjectInformation Extractionen_US
dc.subjectDigital Librariesen_US
dc.subjectNatural Language Processingen_US
dc.subject.otherdigital librariesen_US
dc.subject.othermulti-document summarizationen_US
dc.subject.otherautomatic summarizationen_US
dc.subject.otherabstractingen_US
dc.subject.othersummarizationen_US
dc.titleAutomatic multi-document summarization for digital librariesen_US
dc.typeConference Paperen_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.