Academic Commons

Articles

Sentence Fusion for Multidocument News Summarization

McKeown, Kathleen; Barzilay, Regina

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.

Subjects

Files

  • thumnail for J05-3002McKeown_sentence_fusion_for_multidocument_news_summarization.pdf J05-3002McKeown_sentence_fusion_for_multidocument_news_summarization.pdf application/pdf 1.11 MB Download File

Also Published In

Title
Computational Linguistics
DOI
https://doi.org/10.1162/089120105774321091

More About This Work

Academic Units
Computer Science
Published Here
April 8, 2013