Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources

TL;DR

This paper introduces a novel method for improving word embeddings by integrating external lexical knowledge and applying adversarial neural networks, leading to better semantic understanding in tasks like word similarity and dialog state tracking.

Contribution

It proposes a new post-specialization approach using adversarial neural networks with Wasserstein distance to enhance semantic relations in word embeddings.

Findings

Improved performance on word similarity tasks

Enhanced dialog state tracking accuracy

Outperforms state-of-the-art specialization methods

Abstract

In this work, we present an effective method for semantic specialization of word vector representations. To this end, we use traditional word embeddings and apply specialization methods to better capture semantic relations between words. In our approach, we leverage external knowledge from rich lexical resources such as BabelNet. We also show that our proposed post-specialization method based on an adversarial neural network with the Wasserstein distance allows to gain improvements over state-of-the-art methods on two tasks: word similarity and dialog state tracking.