Synonymy graph connectivity in graph-based word sense induction

Abstract

In this paper, we present an approach for synonymy graph augmentation. The approach is based on the equivalence property of the synonymy relation and implies the addition of the missing transitive edges between the potential synonyms in the input synonymy graph. We also conduct the preliminary evaluation of this approach on two datasets for the Russian language and show that it does increase the quality of the graph clustering comparing to the non-augmented input graph.