Stochastic Distributional Models for Textual Information Retrieval

The objective of this paper is to present a textual similarity model for Information Retrieval (IR) based on the Distributional Semantic (DS) model. This model is an extension of the standard Vector Space model, which further takes into account the co-frequencies between the terms in a given reference corpus, that are considered to provide a distributional representation of the "semantics" of the terms. Practical retrieval experiments using DSbased similarity models have been conducted in the framework of the AMARYLLIS evaluation campaign. The results obtained are presented, and indicate significant improvement of the performance in comparison with the standard approach. keywords :Textual similarity, Information Retrieval, Distributional Semantics.