Automatic summarization of search engine hit lists

  • Authors:
  • Dragomir R. Radev;Weiguo Fan

  • Affiliations:
  • University of Michigan, Ann Arbor, MI;University of Michigan Business School, Ann Arbor, MI

  • Venue:
  • RANLPIR '00 Proceedings of the ACL-2000 workshop on Recent advances in natural language processing and information retrieval: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 11
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present our work on open-domain multi-document summarization in the framework of Web search. Our system, SNS (pronounced "essence"), retrieves documents related to an unrestricted user query and summarizes a subset of them as selected by the user. We present a task-based extrinsic evaluation of the quality of the produced multi-document summaries. The evaluation results show that summarization quality is relatively high and does help improve the reading speed and judge the relevance of the retrieved URLs.