Automatic text summarization
Date of Publication
2005
Document Type
Bachelor's Thesis
Degree Name
Bachelor of Science in Computer Science
Subject Categories
Computer Sciences
College
College of Computer Studies
Department/Unit
Computer Science
Thesis Adviser
Allan B. Borra
Defense Panel Chair
Allan B. Borra
Defense Panel Member
Ethel Ong
Charibeth Ko Cheng
Abstract/Summary
Given an information source, Automatic Text Summarization (ATS) produces the cluster of information which is most relevant to the needs of the user. The three approaches in ATS are the shallow approach, the deeper approach, and the hybrid approach. A common problem with these approaches is that they do not have sufficient coherence. Coherence is the way the parts of the text gather together to form an integrated whole. With today's automatic text summarizers, statements are commonly non-sequitur-meaning a statement that does not follow logically from what preceded it. There is no smooth transition from one idea to another. The driving force of this research is the development of a system that will be able to summarize a given document while still maintaining coherence and salient information in the text. To do this, the system architecture integrated two main existing techniques in ATS: keyword extraction and discourse analysis based on Rhetorical Structure Theory (RST).
Keywords: automatic text summarization, natural language processing, keyword extraction, rhetorical structure theory, coherence.
Abstract Format
html
Language
English
Format
Accession Number
TU13616
Shelf Location
Archives, The Learning Commons, 12F, Henry Sy Sr. Hall
Physical Description
1 v. (various foliations) : ill. (some col.) ; 28 cm.
Keywords
Natural language processing (Computer science); Artificial intelligence; Logic programming; Knowledge representation (Information theory); Coherent states
Recommended Citation
Diola, A. V., Ong Lopez, J. T., So, S. C., & Torraba, P. L. (2005). Automatic text summarization. Retrieved from https://animorepository.dlsu.edu.ph/etd_bachelors/14210