A Hidden Markov Model Approach to Word Sense Disambiguation

  • Authors:
  • Antonio Molina;Ferran Pla;Encarna Segarra

  • Affiliations:
  • -;-;-

  • Venue:
  • IBERAMIA 2002 Proceedings of the 8th Ibero-American Conference on AI: Advances in Artificial Intelligence
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this work, we propose a supervised approach to Word Sense Disambiguation which is based on Specialized Hidden Markov Models and the use of WordNet. Our approach formulates the disambiguation process as a tagging problem. The specialization process allows for the incorporation of additional knowledge into the models. We evaluated our system on the English all-words taskof the Senseval-2 competition. The performance of our system is in line with the best approaches for this task.