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.- Anthology ID:
- 2020.acl-main.356
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3871–3877
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.356
- DOI:
- 10.18653/v1/2020.acl-main.356
- Cite (ACL):
- Oren Barkan, Idan Rejwan, Avi Caciularu, and Noam Koenigstein. 2020. Bayesian Hierarchical Words Representation Learning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3871–3877, Online. Association for Computational Linguistics.
- Cite (Informal):
- Bayesian Hierarchical Words Representation Learning (Barkan et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.acl-main.356.pdf