Journal of Harbin University of Science and Technology (Oct 2019)

A Method of Word Sense Disambiguation with Restricted Boltzmann Machine

  • ZHANG Chun-xiang,
  • LI Hai-rui,
  • GAO Xue-yao

DOI
https://doi.org/10.15938/j.jhust.2019.05.019
Journal volume & issue
Vol. 24, no. 05
pp. 116 – 121

Abstract

Read online

For polysemy phenomenon in Chinese, Restricted Boltzmann Machine (RBM) is adopted to determine the true meaning of ambiguous vocabulary where linguistic knowledge in context is used Word form, part of speech and semantic categories in four left and right lexical units adjacent to an ambiguous word are selected as disambiguation features At the same time, RBM is used to construct word sense disambiguation (WSD) model Training corpus in SemEval-2007: Task#5 and semantic annotation corpus in Harbin Institute of Technology are used to optimize parameters of RBM Test corpus in SemEval-2007: Task#5 is used to evaluate WSD model Experimental results show that compared with Bayesian word sense disambiguation classifier, disambiguation accuracy of WSD method with RBM is improved

Keywords