Learning Type-Driven Tensor-Based Meaning Representations

TL;DR

This paper explores learning 3rd-order tensor representations for transitive verb semantics within a type-driven compositional distributional semantics framework, using neural network techniques and demonstrating promising results.

Contribution

It introduces a neural network-based method for learning tensor representations of transitive verbs in a type-driven semantic framework, advancing compositional distributional semantics.

Findings

Promising results against a competitive baseline

Effective tensor learning for transitive verbs

Potential for extending to higher-dimensional spaces

Abstract

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.