Learning Type-Driven Tensor-Based Meaning Representations
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.
Cite
@article{arxiv.1312.5985,
title = {Learning Type-Driven Tensor-Based Meaning Representations},
author = {Tamara Polajnar and Luana Fagarasan and Stephen Clark},
journal= {arXiv preprint arXiv:1312.5985},
year = {2014}
}
Comments
Submitted as part of the open review process for ICLR'14. The paper contains 10 pages, 3 figures, 4 tables