Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language

TL;DR

This paper introduces an information-based semantic similarity measure within taxonomies, outperforming traditional methods, and applies it to resolve ambiguity in natural language through algorithms validated by experiments.

Contribution

It proposes a novel shared information content measure for semantic similarity in taxonomies and demonstrates its effectiveness in ambiguity resolution tasks.

Findings

The information-based measure outperforms edge-counting methods.

Algorithms leveraging taxonomic similarity effectively resolve ambiguity.

Experimental results confirm improved performance in natural language tasks.

Abstract

This article presents a measure of semantic similarity in an IS-A taxonomy based on the notion of shared information content. Experimental evaluation against a benchmark set of human similarity judgments demonstrates that the measure performs better than the traditional edge-counting approach. The article presents algorithms that take advantage of taxonomic similarity in resolving syntactic and semantic ambiguity, along with experimental results demonstrating their effectiveness.