@inproceedings{shareghi-etal-2019-bayesian,
title = "{B}ayesian Learning for Neural Dependency Parsing",
author = "Shareghi, Ehsan and
Li, Yingzhen and
Zhu, Yi and
Reichart, Roi and
Korhonen, Anna",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1354",
doi = "10.18653/v1/N19-1354",
pages = "3509--3519",
abstract = "While neural dependency parsers provide state-of-the-art accuracy for several languages, they still rely on large amounts of costly labeled training data. We demonstrate that in the small data regime, where uncertainty around parameter estimation and model prediction matters the most, Bayesian neural modeling is very effective. In order to overcome the computational and statistical costs of the approximate inference step in this framework, we utilize an efficient sampling procedure via stochastic gradient Langevin dynamics to generate samples from the approximated posterior. Moreover, we show that our Bayesian neural parser can be further improved when integrated into a multi-task parsing and POS tagging framework, designed to minimize task interference via an adversarial procedure. When trained and tested on 6 languages with less than 5k training instances, our parser consistently outperforms the strong bilstm baseline (Kiperwasser and Goldberg, 2016). Compared with the biaffine parser (Dozat et al., 2017) our model achieves an improvement of up to 3{\%} for Vietnames and Irish, while our multi-task model achieves an improvement of up to 9{\%} across five languages: Farsi, Russian, Turkish, Vietnamese, and Irish.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shareghi-etal-2019-bayesian">
<titleInfo>
<title>Bayesian Learning for Neural Dependency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Shareghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingzhen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While neural dependency parsers provide state-of-the-art accuracy for several languages, they still rely on large amounts of costly labeled training data. We demonstrate that in the small data regime, where uncertainty around parameter estimation and model prediction matters the most, Bayesian neural modeling is very effective. In order to overcome the computational and statistical costs of the approximate inference step in this framework, we utilize an efficient sampling procedure via stochastic gradient Langevin dynamics to generate samples from the approximated posterior. Moreover, we show that our Bayesian neural parser can be further improved when integrated into a multi-task parsing and POS tagging framework, designed to minimize task interference via an adversarial procedure. When trained and tested on 6 languages with less than 5k training instances, our parser consistently outperforms the strong bilstm baseline (Kiperwasser and Goldberg, 2016). Compared with the biaffine parser (Dozat et al., 2017) our model achieves an improvement of up to 3% for Vietnames and Irish, while our multi-task model achieves an improvement of up to 9% across five languages: Farsi, Russian, Turkish, Vietnamese, and Irish.</abstract>
<identifier type="citekey">shareghi-etal-2019-bayesian</identifier>
<identifier type="doi">10.18653/v1/N19-1354</identifier>
<location>
<url>https://aclanthology.org/N19-1354</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>3509</start>
<end>3519</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bayesian Learning for Neural Dependency Parsing
%A Shareghi, Ehsan
%A Li, Yingzhen
%A Zhu, Yi
%A Reichart, Roi
%A Korhonen, Anna
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F shareghi-etal-2019-bayesian
%X While neural dependency parsers provide state-of-the-art accuracy for several languages, they still rely on large amounts of costly labeled training data. We demonstrate that in the small data regime, where uncertainty around parameter estimation and model prediction matters the most, Bayesian neural modeling is very effective. In order to overcome the computational and statistical costs of the approximate inference step in this framework, we utilize an efficient sampling procedure via stochastic gradient Langevin dynamics to generate samples from the approximated posterior. Moreover, we show that our Bayesian neural parser can be further improved when integrated into a multi-task parsing and POS tagging framework, designed to minimize task interference via an adversarial procedure. When trained and tested on 6 languages with less than 5k training instances, our parser consistently outperforms the strong bilstm baseline (Kiperwasser and Goldberg, 2016). Compared with the biaffine parser (Dozat et al., 2017) our model achieves an improvement of up to 3% for Vietnames and Irish, while our multi-task model achieves an improvement of up to 9% across five languages: Farsi, Russian, Turkish, Vietnamese, and Irish.
%R 10.18653/v1/N19-1354
%U https://aclanthology.org/N19-1354
%U https://doi.org/10.18653/v1/N19-1354
%P 3509-3519
Markdown (Informal)
[Bayesian Learning for Neural Dependency Parsing](https://aclanthology.org/N19-1354) (Shareghi et al., NAACL 2019)
ACL
- Ehsan Shareghi, Yingzhen Li, Yi Zhu, Roi Reichart, and Anna Korhonen. 2019. Bayesian Learning for Neural Dependency Parsing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3509–3519, Minneapolis, Minnesota. Association for Computational Linguistics.