Lexical cohesion based topic modeling for summarization

Date
2008-02
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
International Conference on Intelligent Text Processing and Computational Linguistics CICLing 2008: Computational Linguistics and Intelligent Text Processing
Print ISSN
Electronic ISSN
Publisher
Springer
Volume
Issue
Pages
582 - 592
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Series
Abstract

In this paper, we attack the problem of forming extracts for text summarization. Forming extracts involves selecting the most representative and significant sentences from the text. Our method takes advantage of the lexical cohesion structure in the text in order to evaluate significance of sentences. Lexical chains have been used in summarization research to analyze the lexical cohesion structure and represent topics in a text. Our algorithm represents topics by sets of co-located lexical chains to take advantage of more lexical cohesion clues. Our algorithm segments the text with respect to each topic and finds the most important topic segments. Our summarization algorithm has achieved better results, compared to some other lexical chain based algorithms. © 2008 Springer-Verlag Berlin Heidelberg.

Course
Other identifiers
Book Title
Keywords
Lexical chains, Lexical cohesion, Text summarization, Adhesion, Computational linguistics, Linguistics, Word processing, Intelligent text processing, International conferences, Lexical cohesion structure, Text processing
Citation
Published Version (Please cite this version)