摘要：This paper analyses a measure of semantic relatedness between two words. Our measure is based on shortest path between synsets in WordNet v2.0. It uses all available links in WordNet v2.0 and is implemented by a bidirectional breadth-first algorithm. Experimental evaluation and comparison with a benchmark set of human similarity judgments demonstrates that the simple measure applied on WordNet v2.0 performs better than the more complicated approaches mostly combining an IS-A taxonomy with the notion of shared information content extracted from corpora. One explanation is that our pretty basic method efficiently exploits all the available links in WordNet v2.0, while other measures, although more complicated and advanced, do not make good use of the new derivational links added to WordNet in the latest version 2.0.
