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.
Oren Barkan, Idan Rejwan, Avi Caciularu, and Noam Koenigstein. 2020.Bayesian Hierarchical Words Representation Learning. InProceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3871–3877, Online. Association for Computational Linguistics.
@inproceedings{barkan-etal-2020-bayesian, title = "{B}ayesian Hierarchical Words Representation Learning", author = "Barkan, Oren and Rejwan, Idan and Caciularu, Avi and Koenigstein, Noam", editor = "Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel", booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", month = jul, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.acl-main.356/", doi = "10.18653/v1/2020.acl-main.356", pages = "3871--3877", 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."}
%0 Conference Proceedings%T Bayesian Hierarchical Words Representation Learning%A Barkan, Oren%A Rejwan, Idan%A Caciularu, Avi%A Koenigstein, Noam%Y Jurafsky, Dan%Y Chai, Joyce%Y Schluter, Natalie%Y Tetreault, Joel%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics%D 2020%8 July%I Association for Computational Linguistics%C Online%F barkan-etal-2020-bayesian%X 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.%R 10.18653/v1/2020.acl-main.356%U https://aclanthology.org/2020.acl-main.356/%U https://doi.org/10.18653/v1/2020.acl-main.356%P 3871-3877
Oren Barkan, Idan Rejwan, Avi Caciularu, and Noam Koenigstein. 2020.Bayesian Hierarchical Words Representation Learning. InProceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3871–3877, Online. Association for Computational Linguistics.