Automatic multi-document summarization using a variable-based framework.

This study was in the area of automatic multi-document summarization. The objective of this study was to develop a method for the automatic construction of summaries of sociology dissertation abstracts, focusing on research concepts and their research relationships. A variable-based framework was pr...

Full description

Bibliographic Details
Main Author: Ou, Shiyan.
Other Authors: Khoo, Christopher Soo Guan
Format: Thesis
Published: 2008
Subjects:
Online Access:http://hdl.handle.net/10356/1660
_version_ 1811686171357478912
author Ou, Shiyan.
author2 Khoo, Christopher Soo Guan
author_facet Khoo, Christopher Soo Guan
Ou, Shiyan.
author_sort Ou, Shiyan.
collection NTU
description This study was in the area of automatic multi-document summarization. The objective of this study was to develop a method for the automatic construction of summaries of sociology dissertation abstracts, focusing on research concepts and their research relationships. A variable-based framework was proposed to integrate and organize the four kinds of information extracted from different dissertation abstracts, i.e. research concepts and their research relationships, contextual relations and research methods. A hybrid summarization method involving both extraction and abstraction techniques was developed. It focused more on extraction and integration of research concepts and their research relationships across dissertation abstracts and presenting the integrated information in a Web-based interface. The evaluation results indicated that the variable-based summaries were preferred by the majority of researchers and general users, to the summaries generated by the sentence-extraction methods.
first_indexed 2024-10-01T04:56:10Z
format Thesis
id ntu-10356/1660
institution Nanyang Technological University
last_indexed 2024-10-01T04:56:10Z
publishDate 2008
record_format dspace
spelling ntu-10356/16602019-12-10T14:26:17Z Automatic multi-document summarization using a variable-based framework. Ou, Shiyan. Khoo, Christopher Soo Guan Wee Kim Wee School of Communication and Information DRNTU::Library and information science::Libraries::Automation This study was in the area of automatic multi-document summarization. The objective of this study was to develop a method for the automatic construction of summaries of sociology dissertation abstracts, focusing on research concepts and their research relationships. A variable-based framework was proposed to integrate and organize the four kinds of information extracted from different dissertation abstracts, i.e. research concepts and their research relationships, contextual relations and research methods. A hybrid summarization method involving both extraction and abstraction techniques was developed. It focused more on extraction and integration of research concepts and their research relationships across dissertation abstracts and presenting the integrated information in a Web-based interface. The evaluation results indicated that the variable-based summaries were preferred by the majority of researchers and general users, to the summaries generated by the sentence-extraction methods. Doctor of Philosophy (SCI) 2008-09-10T08:35:07Z 2008-09-10T08:35:07Z 2006 2006 Thesis http://hdl.handle.net/10356/1660 Nanyang Technological University application/pdf
spellingShingle DRNTU::Library and information science::Libraries::Automation
Ou, Shiyan.
Automatic multi-document summarization using a variable-based framework.
title Automatic multi-document summarization using a variable-based framework.
title_full Automatic multi-document summarization using a variable-based framework.
title_fullStr Automatic multi-document summarization using a variable-based framework.
title_full_unstemmed Automatic multi-document summarization using a variable-based framework.
title_short Automatic multi-document summarization using a variable-based framework.
title_sort automatic multi document summarization using a variable based framework
topic DRNTU::Library and information science::Libraries::Automation
url http://hdl.handle.net/10356/1660
work_keys_str_mv AT oushiyan automaticmultidocumentsummarizationusingavariablebasedframework