Efficient Ranking and Computation of Semantic Relatedness and its Application to Word Sense Disambiguation

Wikipedia has grown into a high quality up-to-date knowledge base and can enable many intelligent systems that rely on semantic information. One of the most general and quite powerful semantic tools is a measure of semantic relatedness between concepts. Moreover, the ability to efficiently produce a list of ranked similar concepts for a given concept is very important for a wide range of applications. We propose to use a simple measure of similarity between Wikipedia concepts, based on Dice’s measure, and provide very efficient heuristic methods to compute top k ranking results. We also present a randomized algorithm that speeds up the evaluation of the measure for a pair of articles. Furthermore, since our heuristics are based on statistical properties of scale-free networks, we show that these heuristics are applicable to other complex ontologies. Finally, in order to evaluate the measure, we have used it to solve the problem of word-sense disambiguation. Our approach to word sense disambiguation is based solely on the similarity measure and produces results with high accuracy.