A Structured Distributional Semantic Model: Integrating Structure with Semantics

In this paper we present a novel approach (SDSM) that incorporates structure in distributional semantics. SDSM represents meaning as relation specific distributions over syntactic neighborhoods. We empirically show that the model can effectively represent the semantics of single words and provides significant advantages when dealing with phrasal units that involve word composition. In particular, we demonstrate that our model outperforms both state-of-the-art window-based word embeddings as well as simple approaches for composing distributional semantic representations on an artificial task of verb sense disambiguation and a real-world application of judging event coreference.