Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources
Computation and Language
2020-08-06 v1 Machine Learning
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.
Cite
@article{arxiv.2005.10048,
title = {Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources},
author = {Magdalena Biesialska and Bardia Rafieian and Marta R. Costa-jussà},
journal= {arXiv preprint arXiv:2005.10048},
year = {2020}
}
Comments
Accepted to ACL 2020 SRW