Sentence fusion for multidocument news summarization

  • Authors:
  • Regina Barzilay;Kathleen R. McKeown

  • Affiliations:
  • Massachusetts Institute of Technology regina@csail.mit.edu;Columbia University kathy@cs.columbia.edu

  • Venue:
  • Computational Linguistics
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

A system that can produce informative summaries, highlighting common information found in many online documents, will help Web users to pinpoint information that they need without extensive reading. In this article, we introduce sentence fusion, a novel text-to-text generation technique for synthesizing common information across documents. Sentence fusion involves bottom-up local multisequence alignment to identify phrases conveying similar information and statistical generation to combine common phrases into a sentence. Sentence fusion moves the summarization field from the use of purely extractive methods to the generation of abstracts that contain sentences not found in any of the input documents and can synthesize information across sources.