Automatic interpretation of noun compounds using wordnet similarity

  • Authors:
  • Su Nam Kim;Timothy Baldwin

  • Affiliations:
  • Computer Science, University of Illinois, Chicago, IL;Computer Science and Software Engineering, University of Melbourne, Victoria, Australia

  • Venue:
  • IJCNLP'05 Proceedings of the Second international joint conference on Natural Language Processing
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper introduces a method for interpreting novel noun compounds with semantic relations. The method is built around word similarity with pre-tagged noun compounds, based on WordNet::Similarity. Over 1,088 training instances and 1,081 test instances from the Wall Street Journal in the Penn Treebank, the proposed method was able to correctly classify 53.3% of the test noun compounds. We also investigated the relative contribution of the modifier and the head noun in noun compounds of different semantic types.