Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semantics
This work addresses the need for incremental semantic models in dialogue systems, though it appears incremental in nature as it builds on existing theories.
The paper tackles the problem of modeling semantic processing in dialogue by requiring incrementality, and demonstrates that Dynamic Syntax can be assigned a compositional distributional semantics using tensor contraction, enabling incremental assignment of semantic plausibility measures.
One of the fundamental requirements for models of semantic processing in dialogue is incrementality: a model must reflect how people interpret and generate language at least on a word-by-word basis, and handle phenomena such as fragments, incomplete and jointly-produced utterances. We show that the incremental word-by-word parsing process of Dynamic Syntax (DS) can be assigned a compositional distributional semantics, with the composition operator of DS corresponding to the general operation of tensor contraction from multilinear algebra. We provide abstract semantic decorations for the nodes of DS trees, in terms of vectors, tensors, and sums thereof; using the latter to model the underspecified elements crucial to assigning partial representations during incremental processing. As a working example, we give an instantiation of this theory using plausibility tensors of compositional distributional semantics, and show how our framework can incrementally assign a semantic plausibility measure as it parses phrases and sentences.