Open-domain question: answering

  • Authors:
  • John Prager

  • Affiliations:
  • IBM T.J. Watson Research Center, Yorktown Heights, NY

  • Venue:
  • Foundations and Trends in Information Retrieval
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

The top-performing Question-Answering (QA) systems have been of two types: consistent, solid, well-established and multi-faceted systems that do well year after year, and ones that come out of nowhere employing totally innovative approaches and which out-perform almost everybody else. This article examines both types of system in depth. We establish what a "typical" QA-system looks like, and cover the commonly used approaches by the component modules. Understanding this will enable any proficient system developer to build his own QA-system. Fortunately there are many components available for free from their developers to make this a reasonable expectation for a graduate-level project. We also look at particular systems that have performed well and which employ interesting and innovative approaches.