Robust and Efficient Page Rank for Word Sense Disambiguation

Abstract

Graph-based methods that are en vogue in the social network analysis area, such as centrality models, have been recently applied to linguistic knowledge bases, including unsupervised Word Sense Disambiguation. Although the achievable accuracy is rather high, the main drawback of these methods is the high computational demanding whenever applied to the large scale sense repositories. In this paper an adaptation of the PageRank algorithm recently proposed for Word Sense Disambiguation is presented that preserves the reachable accuracy while significantly reducing the requested processing time. Experimental analysis over well-known benchmarks will be presented in the paper and the results confirm our hypothesis. 1