Bayesian Hierarchical Words Representation Learning

Oren Barkan; Idan Rejwan; Noam Koenigstein

doi:https://doi.org/https://arxiv.org/ftp/arxiv/papers/2004/2004.07126.pdf

Bayesian Hierarchical Words Representation Learning

Oren Barkan, Idan Rejwan, Noam Koenigstein

Open University of Israel, Bar-Ilan University, Tel Aviv University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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.

Original language	English
Title of host publication	ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	3871-3877
Number of pages	7
ISBN (Electronic)	9781952148255
DOIs	https://doi.org/https://arxiv.org/ftp/arxiv/papers/2004/2004.07126.pdf
State	Published - 2020
Event	58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 - Virtual, Online, United States Duration: 5 Jul 2020 → 10 Jul 2020

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics

Conference

Conference	58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Country/Territory	United States
City	Virtual, Online
Period	5/07/20 → 10/07/20

All Science Journal Classification (ASJC) codes

Language and Linguistics
Computer Science Applications
Linguistics and Language

Access to Document

https://doi.org/https://arxiv.org/ftp/arxiv/papers/2004/2004.07126.pdf

Cite this

Barkan, O., Rejwan, I., & Koenigstein, N. (2020). Bayesian Hierarchical Words Representation Learning. In ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 3871-3877). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics (ACL). https://doi.org/https://arxiv.org/ftp/arxiv/papers/2004/2004.07126.pdf

Barkan, Oren ; Rejwan, Idan ; Koenigstein, Noam. / Bayesian Hierarchical Words Representation Learning. ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. pp. 3871-3877 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{a5c137c148434858a8a9396569c7dd65,

title = "Bayesian Hierarchical Words Representation 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.",

author = "Oren Barkan and Idan Rejwan and Noam Koenigstein",

note = "Publisher Copyright: {\textcopyright} 2020 Association for Computational Linguistics; 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 ; Conference date: 05-07-2020 Through 10-07-2020",

year = "2020",

doi = "https://doi.org/https://arxiv.org/ftp/arxiv/papers/2004/2004.07126.pdf",

language = "English",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

pages = "3871--3877",

booktitle = "ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

address = "United States",

}

Barkan, O, Rejwan, I & Koenigstein, N 2020, Bayesian Hierarchical Words Representation Learning. in ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 3871-3877, 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Virtual, Online, United States, 5/07/20. https://doi.org/https://arxiv.org/ftp/arxiv/papers/2004/2004.07126.pdf

Bayesian Hierarchical Words Representation Learning. / Barkan, Oren; Rejwan, Idan; Koenigstein, Noam.
ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. p. 3871-3877 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Bayesian Hierarchical Words Representation Learning

AU - Barkan, Oren

AU - Rejwan, Idan

AU - Koenigstein, Noam

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85092713013&partnerID=8YFLogxK

U2 - https://doi.org/https://arxiv.org/ftp/arxiv/papers/2004/2004.07126.pdf

DO - https://doi.org/https://arxiv.org/ftp/arxiv/papers/2004/2004.07126.pdf

M3 - Conference contribution

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 3871

EP - 3877

BT - ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

Y2 - 5 July 2020 through 10 July 2020

ER -

Barkan O, Rejwan I, Koenigstein N. Bayesian Hierarchical Words Representation Learning. In ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 3871-3877. (Proceedings of the Annual Meeting of the Association for Computational Linguistics). doi: https://doi.org/https://arxiv.org/ftp/arxiv/papers/2004/2004.07126.pdf

Bayesian Hierarchical Words Representation Learning

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this