Bayesian Hierarchical Words Representation Learning
Computation and Language
2020-04-16 v1 Machine Learning
Machine Learning
Abstract
This paper presents the Bayesian Hierarchical Words Representation (BHWR) learning algorithm. BHWR facilitates Variational Bayes word representation learning combined with semantic taxonomy modeling via hierarchical priors. By propagating relevant information between related words, BHWR utilizes the taxonomy to improve the quality of such representations. Evaluation of several linguistic datasets demonstrates the advantages of BHWR over suitable alternatives that facilitate Bayesian modeling with or without semantic priors. Finally, we further show that BHWR produces better representations for rare words.
Cite
@article{arxiv.2004.07126,
title = {Bayesian Hierarchical Words Representation Learning},
author = {Oren Barkan and Idan Rejwan and Avi Caciularu and Noam Koenigstein},
journal= {arXiv preprint arXiv:2004.07126},
year = {2020}
}
Comments
Accepted to ACL 2020