An application of latent semantic analysis to word sense discrimination for words with related and unrelated meanings

  • Authors:
  • Juan Pino;Maxine Eskenazi

  • Affiliations:
  • Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA

  • Venue:
  • EdAppsNLP '09 Proceedings of the Fourth Workshop on Innovative Use of NLP for Building Educational Applications
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an application of Latent Semantic Analysis to word sense discrimination within a tutor for English vocabulary learning. We attempt to match the meaning of a word in a document with the meaning of the same word in a fill-in-the-blank question. We compare the performance of the Lesk algorithm to Latent Semantic Analysis. We also compare the performance of Latent Semantic Analysis on a set of words with several unrelated meanings and on a set of words having both related and unrelated meanings.