In this paper we present a novel approach (SDSM) that incorporates structure in dis- tributional semantics. SDSM represents meaning as relation specific distributions over syntactic neighborhoods. We em- pirically show that the model can effec- tively represent the semantics of single words and provides significant advantages when dealing with phrasal units that in- volve 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 rep- resentations on an artificial task of verb sense disambiguation and a real-world ap- plication of judging event coreference.

Click Here to View the Paper In XML Format