Coreference for NLP applications

  • Authors:
  • Thomas S. Morton

  • Affiliations:
  • University of Pennsylvania, Philadelphia, PA

  • Venue:
  • ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
  • Year:
  • 2000

Quantified Score

Hi-index 0.02

Visualization

Abstract

This paper presents several techniques for performing automatic coreference annotation and performance results for each of them. To demonstrate that they can be applied to real-world data, we have built a simple question-answering system which uses the techniques. A system using coreference is compared to a baseline system with the result that the addition of the coreference annotation improves performance.