Counter-fitting Word Vectors to Linguistic Constraints

TL;DR

This paper introduces a counter-fitting technique that adjusts pre-trained word vectors by incorporating linguistic constraints, enhancing semantic similarity judgments and improving dialogue state tracking performance.

Contribution

The novel counter-fitting method effectively integrates antonymy and synonymy constraints into existing word vectors, achieving state-of-the-art results and better domain adaptation.

Findings

State-of-the-art on SimLex-999 dataset

Improved dialogue state tracking across domains

Enhanced semantic similarity judgments

Abstract

In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity. Applying this method to publicly available pre-trained word vectors leads to a new state of the art performance on the SimLex-999 dataset. We also show how the method can be used to tailor the word vector space for the downstream task of dialogue state tracking, resulting in robust improvements across different dialogue domains.