articleAug 9, 2003Closed access

Extended gloss overlaps as a measure of semantic relatedness

Carnegie Mellon University · University of Minnesota, Duluth

Abstract

This paper presents a new measure of semantic relatedness between concepts that is based on the number of shared words (overlaps) in their definitions (glosses). This measure is unique in that it extends the glosses of the concepts under consideration to include the glosses of other concepts to which they are related according to a given concept hierarchy. We show that this new measure reasonably correlates to human judgments. We introduce a new method of word sense disambiguation based on extended gloss overlaps, and demonstrate that it fares well on the SENSEVAL-2 lexical sample data. 1

Citation impact

720
total citations
FWCI
29.50
Percentile
100%
References
11
Citations per year

Authors

2

Topics & keywords

Keywords
  • Gloss (optics)
  • Measure (data warehouse)
  • Computer science
  • Natural language processing
  • Artificial intelligence
  • Semantic similarity
  • Hierarchy
  • Data mining
No related works found for this paper.