Learning Type-Driven Tensor-Based Meaning Representations
This work addresses a specific problem in compositional distributional semantics for natural language processing, but it is incremental as it builds on existing neural network techniques and focuses narrowly on transitive verbs.
The paper tackles learning 3rd-order tensors to represent transitive verb semantics in a type-driven tensor-based framework, achieving promising results against a competitive baseline in a selectional preference task.
This paper investigates the learning of 3rd-order tensors representing the semantics of transitive verbs. The meaning representations are part of a type-driven tensor-based semantic framework, from the newly emerging field of compositional distributional semantics. Standard techniques from the neural networks literature are used to learn the tensors, which are tested on a selectional preference-style task with a simple 2-dimensional sentence space. Promising results are obtained against a competitive corpus-based baseline. We argue that extending this work beyond transitive verbs, and to higher-dimensional sentence spaces, is an interesting and challenging problem for the machine learning community to consider.