From Global to Local Similarities: A Graph-Based Contextualization Method using Distributional Thesauri

After recasting the computation of a distributional thesaurus in a graph-based framework for term similarity, we introduce a new contextualization method that generates, for each term occurrence in a text, a ranked list of terms that are semantically similar and compatible with the given context. The framework is instantiated by the definition of term and context, which we derive from dependency parses in this work. Evaluating our approach on a standard data set for lexical substitution, we show substantial improvements over a strong non-contextualized baseline across all parts of speech. In contrast to comparable approaches, our framework defines an unsupervised generative method for similarity in context and does not rely on the existence of lexical resources as a source for candidate expansions.