Grounded learning for compositional vector semantics
This work addresses the integration of vector-based semantics with biologically plausible neural networks for cognitive science applications, though it appears incremental in scope.
The paper tackles the problem of implementing compositional distributional semantics in a spiking neural network to enhance cognitive plausibility and address concept binding issues, resulting in a small implementation and a method for training word representations using labelled images.
Categorical compositional distributional semantics is an approach to modelling language that combines the success of vector-based models of meaning with the compositional power of formal semantics. However, this approach was developed without an eye to cognitive plausibility. Vector representations of concepts and concept binding are also of interest in cognitive science, and have been proposed as a way of representing concepts within a biologically plausible spiking neural network. This work proposes a way for compositional distributional semantics to be implemented within a spiking neural network architecture, with the potential to address problems in concept binding, and give a small implementation. We also describe a means of training word representations using labelled images.