Resolving Lexical Ambiguity in Tensor Regression Models of Meaning

TL;DR

This paper introduces an explicit disambiguation step to enhance tensor-based compositional models of meaning, demonstrating improved performance across experiments and suggesting broad applicability.

Contribution

It presents a novel disambiguation method integrated into tensor regression models, improving their ability to handle lexical ambiguity in semantic composition.

Findings

Disambiguation improves model performance

Method is effective across different models

Results are consistent in multiple experiments

Abstract

This paper provides a method for improving tensor-based compositional distributional models of meaning by the addition of an explicit disambiguation step prior to composition. In contrast with previous research where this hypothesis has been successfully tested against relatively simple compositional models, in our work we use a robust model trained with linear regression. The results we get in two experiments show the superiority of the prior disambiguation method and suggest that the effectiveness of this approach is model-independent.