Computer Laboratory

Technical reports

Between shallow and deep: an experiment in automatic summarising

R.I. Tucker, K. Spärck Jones

April 2005, 34 pages


This paper describes an experiment in automatic summarising using a general-purpose strategy based on a compromise between shallow and deep processing. The method combines source text analysis into simple logical forms with the use of a semantic graph for representation and operations on the graph to identify summary content.

The graph is based on predications extracted from the logical forms, and the summary operations apply three criteria, namely importance, representativeness, and cohesiveness, in choosing node sets to form the content representation for the summary. This is used in different ways for output summaries. The paper presents the motivation for the strategy, details of the CLASP system, and the results of initial testing and evaluation on news material.

Full text

PDF (0.3 MB)

BibTeX record

  author =	 {Tucker, R.I. and Sp{\"a}rck Jones, K.},
  title = 	 {{Between shallow and deep: an experiment in automatic
  year = 	 2005,
  month = 	 apr,
  url = 	 {},
  institution =  {University of Cambridge, Computer Laboratory},
  number = 	 {UCAM-CL-TR-632}