Word-sense disambiguation using statistical methods

  • Authors:
  • Peter F. Brown;Stephen A. Della Pietra;Vincent J. Della Pietra;Robert L. Mercer

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

  • Venue:
  • ACL '91 Proceedings of the 29th annual meeting on Association for Computational Linguistics
  • Year:
  • 1991

Quantified Score

Hi-index 0.00

Visualization

Abstract

We describe a statistical technique for assigning senses to words. An instance of a word is assigned a sense by asking a question about the context in which the word appears. The question is constructed to have high mutual information with the translation of that instance in another language. When we incorporated this method of assigning senses into our statistical machine translation system, the error rate of the system decreased by thirteen percent.