Unsupervised Italian word sense disambiguation using WordNets and unlabeled corpora

  • Authors:
  • Radu Florian;Richard Wicentowski

  • Affiliations:
  • Johns Hopkins University;Johns Hopkins University

  • Venue:
  • WSD '02 Proceedings of the ACL-02 workshop on Word sense disambiguation: recent successes and future directions - Volume 8
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a novel method for unsupervised word sense disambiguation, which combines multiple information sources, including semantic relations, large unlabeled corpora, and cross-lingual distributional statistics. This method extends and builds on the JHU system that participated in the SENSEVAL2 exercise. Experiments performed on the SENSEVAL2 Italian lexical-sample data show significant improvements over previously published results on this data set.