Generic and Query-Based Text Summarization Using Lexical Cohesion

  • Authors:
  • Yllias Chali

  • Affiliations:
  • -

  • Venue:
  • AI '02 Proceedings of the 15th Conference of the Canadian Society for Computational Studies of Intelligence on Advances in Artificial Intelligence
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

Text summarization addresses the problem of selecting the most important portions of the text and the problem of producing coherent summaries. The goal of this paper is to show how these objectives can be achieved through an efficient use of lexical cohesion. The method addresses both generic and query-based summaries. We present an approach for identifying the most important portions of the text which are topically best suited to represent the source text according to the author's views or in response to the user's interests. This identification must also take into consideration the degree of connectiveness among the chosen text portions so as to minimize the danger of producing summaries which contain poorly linked sentences. These objectives can be achieved through an efficient use of lexical cohesion. We present a system that handles these objectives, we discuss the performance of the system, we compare it to other systems, and we outline some future works.