@inproceedings{zhang-etal-2019-posterior,
title = "Posterior-regularized {REINFORCE} for Instance Selection in Distant Supervision",
author = "Zhang, Qi and
Tang, Siliang and
Ren, Xiang and
Wu, Fei and
Pu, Shiliang and
Zhuang, Yueting",
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/N19-1290",
doi = "10.18653/v1/N19-1290",
pages = "2831--2835",
abstract = "This paper provides a new way to improve the efficiency of the REINFORCE training process. We apply it to the task of instance selection in distant supervision. Modeling the instance selection in one bag as a sequential decision process, a reinforcement learning agent is trained to determine whether an instance is valuable or not and construct a new bag with less noisy instances. However unbiased methods, such as REINFORCE, could usually take much time to train. This paper adopts posterior regularization (PR) to integrate some domain-specific rules in instance selection using REINFORCE. As the experiment results show, this method remarkably improves the performance of the relation classifier trained on cleaned distant supervision dataset as well as the efficiency of the REINFORCE training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2019-posterior">
<titleInfo>
<title>Posterior-regularized REINFORCE for Instance Selection in Distant Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siliang</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiliang</namePart>
<namePart type="family">Pu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yueting</namePart>
<namePart type="family">Zhuang</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>This paper provides a new way to improve the efficiency of the REINFORCE training process. We apply it to the task of instance selection in distant supervision. Modeling the instance selection in one bag as a sequential decision process, a reinforcement learning agent is trained to determine whether an instance is valuable or not and construct a new bag with less noisy instances. However unbiased methods, such as REINFORCE, could usually take much time to train. This paper adopts posterior regularization (PR) to integrate some domain-specific rules in instance selection using REINFORCE. As the experiment results show, this method remarkably improves the performance of the relation classifier trained on cleaned distant supervision dataset as well as the efficiency of the REINFORCE training.</abstract>
<identifier type="citekey">zhang-etal-2019-posterior</identifier>
<identifier type="doi">10.18653/v1/N19-1290</identifier>
<location>
<url>https://aclanthology.org/N19-1290</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2831</start>
<end>2835</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Posterior-regularized REINFORCE for Instance Selection in Distant Supervision
%A Zhang, Qi
%A Tang, Siliang
%A Ren, Xiang
%A Wu, Fei
%A Pu, Shiliang
%A Zhuang, Yueting
%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 zhang-etal-2019-posterior
%X This paper provides a new way to improve the efficiency of the REINFORCE training process. We apply it to the task of instance selection in distant supervision. Modeling the instance selection in one bag as a sequential decision process, a reinforcement learning agent is trained to determine whether an instance is valuable or not and construct a new bag with less noisy instances. However unbiased methods, such as REINFORCE, could usually take much time to train. This paper adopts posterior regularization (PR) to integrate some domain-specific rules in instance selection using REINFORCE. As the experiment results show, this method remarkably improves the performance of the relation classifier trained on cleaned distant supervision dataset as well as the efficiency of the REINFORCE training.
%R 10.18653/v1/N19-1290
%U https://aclanthology.org/N19-1290
%U https://doi.org/10.18653/v1/N19-1290
%P 2831-2835
Markdown (Informal)
[Posterior-regularized REINFORCE for Instance Selection in Distant Supervision](https://aclanthology.org/N19-1290) (Zhang et al., NAACL 2019)
ACL
- Qi Zhang, Siliang Tang, Xiang Ren, Fei Wu, Shiliang Pu, and Yueting Zhuang. 2019. Posterior-regularized REINFORCE for Instance Selection in Distant Supervision. 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 2831–2835, Minneapolis, Minnesota. Association for Computational Linguistics.