Chapter

Advances in Artificial Intelligence

Volume 1952 of the series Lecture Notes in Computer Science pp 329-338

Summary Generation and Evaluation in SumUM

  • Horacio SaggionAffiliated withDIRO - Université de Montréal
  • , Guy LapalmeAffiliated withDIRO - Université de Montréal

* Final gross prices may vary according to local VAT.

Get Access

Abstract

We describe and evaluate SumUM, a text summarization system that produces indicative-informative abstracts for technical papers. Our approach consists of the shallow syntactic and conceptual analysis of the source document and of the implementation of text re-generation techniques based on a study of abstracts produced by professional abstractors. In an evaluation of indicative content in a categorization task, we observed no differences with other automatic method, while differences are observed in an evaluation of informative content. In an evaluation of text quality, the abstracts were considered acceptable when compared with other automatic abstracts.