Automatic multi-document summarization for digital libraries

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

dc.contributor.author	Ou, Shiyan
dc.contributor.author	Khoo, Christopher S.G.
dc.contributor.author	Goh, Dion H.
dc.contributor.editor	Khoo, C.	en_US
dc.contributor.editor	Singh, D.	en_US
dc.contributor.editor	Chaudhry, A.S.	en_US
dc.date.accessioned	2007-05-22T00:00:01Z
dc.date.available	2010-06-18T23:38:44Z
dc.date.issued	2006	en_US
dc.date.submitted	2007-05-22	en_US
dc.identifier.citation	Automatic multi-document summarization for digital libraries 2006, :72-82	en_US
dc.identifier.uri	http://hdl.handle.net/10150/106042
dc.description.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.
dc.format.mimetype	application/pdf	en_US
dc.language.iso	en	en_US
dc.publisher	School of Communication & Information, Nanyang Technological University	en_US
dc.subject	Information Extraction	en_US
dc.subject	Digital Libraries	en_US
dc.subject	Natural Language Processing	en_US
dc.subject.other	digital libraries	en_US
dc.subject.other	multi-document summarization	en_US
dc.subject.other	automatic summarization	en_US
dc.subject.other	abstracting	en_US
dc.subject.other	summarization	en_US
dc.title	Automatic multi-document summarization for digital libraries	en_US
dc.type	Conference Paper	en_US
refterms.dateFOA	2018-08-21T16:06:19Z
html.description.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.