Automatic text summarization

• Main Authors: Diola, Almira Mae V., Ong Lopez, Joan Tiffany T., So, Sherwin C., Torraba, Phoebus Ferdiel L.
• Format: text
• Language: English
• Published: Animo Repository 2005
• Subjects: Natural language processing (Computer science); Artificial intelligence; Logic programming; Knowledge representation (Information theory); Coherent states; Computer Sciences
• Online Access: https://animorepository.dlsu.edu.ph/etd_bachelors/14210
• Institution: De La Salle University

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.