A question/answer typology with surface text patterns

  • Authors:
  • Eduard Hovy;Ulf Hermjakob;Deepak Ravichandran

  • Affiliations:
  • USC Information Sciences Institute, Marina del Rey, CA;USC Information Sciences Institute, Marina del Rey, CA;USC Information Sciences Institute, Marina del Rey, CA

  • Venue:
  • HLT '02 Proceedings of the second international conference on Human Language Technology Research
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we announce the release of ISI's QA Typology, which is being made available on the web to support the rapid construction of new QA systems. The Typology has been augmented with surface-level patterns associated with answer types, allowing systems to locate answers of the desired type in text by simple string matching. These patterns are extracted from the web automatically. We describe the process of their extraction, compression, and accuracy determination.