Alternative measures of word relatedness in distributional semantics

摘要

This paper presents an alternative method to measuring word-word semantic relatedness in distributional semantics framework. The main idea is to represent target words as rankings of all co-occurring words in a text corpus, ordered by their tf- idf weight and use a metric between rankings (such as Jaro distance or Rank distance) to compute semantic relatedness. This method has several advantages over the standard approach that uses cosine measure in a vector space, mainly in that it is computationally less expensive (i.e. does not require working in a high dimensional space, employing only rankings and a distance which is linear in the rank's length) and presumably more robust. We tested this method on the standard WS-353 Test, obtaining the co-occurrence frequency from the Wacky corpus. The results are comparable to the methods which use vector space models; and, most importantly, the method can be extended to the very challenging task of measuring phrase semantic relatedness.