The Role of Syntax in Vector Space Models of Compositional Semantics
Karl Moritz Hermann and Phil Blunsom
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Sofia, Bulgaria, August 4-9, 2013
Modelling the compositional process by which the meaning of an utterance arises from the meaning of its parts is a fundamental task of Natural Language Processing. In this paper we draw upon recent advances in the learning of vector space representations of sentential semantics and the transparent interface between syntax and semantics provided by Combinatory Categorial Grammar to introduce Combinatory Categorial Autoencoders. This model leverages the CCG combinatory operators to guide a non-linear transformationof meaning within a sentence. We use this model to learn high dimensional embeddings for sentences and evaluate them in a range of tasks, demonstrating that the incorporation of syntax allows a concise model to learn representations that are both effective and general.
Conference Manager (V2.61.0 - Rev. 2792M)