@inproceedings{ren-etal-2020-denoising,
title = "Denoising Multi-Source Weak Supervision for Neural Text Classification",
author = "Ren, Wendi and
Li, Yinghao and
Su, Hanting and
Kartchner, David and
Mitchell, Cassie and
Zhang, Chao",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.334",
doi = "10.18653/v1/2020.findings-emnlp.334",
pages = "3739--3754",
abstract = "We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and incomplete. To address these two challenges, we design a label denoiser, which estimates the source reliability using a conditional soft attention mechanism and then reduces label noise by aggregating rule-annotated weak labels. The denoised pseudo labels then supervise a neural classifier to predicts soft labels for unmatched samples, which address the rule coverage issue. We evaluate our model on five benchmarks for sentiment, topic, and relation classifications. The results show that our model outperforms state-of-the-art weakly-supervised and semi-supervised methods consistently, and achieves comparable performance with fully-supervised methods even without any labeled data. Our code can be found at \url{https://github.com/weakrules/Denoise-multi-weak-sources}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ren-etal-2020-denoising">
<titleInfo>
<title>Denoising Multi-Source Weak Supervision for Neural Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wendi</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinghao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanting</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Kartchner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cassie</namePart>
<namePart type="family">Mitchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and incomplete. To address these two challenges, we design a label denoiser, which estimates the source reliability using a conditional soft attention mechanism and then reduces label noise by aggregating rule-annotated weak labels. The denoised pseudo labels then supervise a neural classifier to predicts soft labels for unmatched samples, which address the rule coverage issue. We evaluate our model on five benchmarks for sentiment, topic, and relation classifications. The results show that our model outperforms state-of-the-art weakly-supervised and semi-supervised methods consistently, and achieves comparable performance with fully-supervised methods even without any labeled data. Our code can be found at https://github.com/weakrules/Denoise-multi-weak-sources.</abstract>
<identifier type="citekey">ren-etal-2020-denoising</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.334</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.334</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3739</start>
<end>3754</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Denoising Multi-Source Weak Supervision for Neural Text Classification
%A Ren, Wendi
%A Li, Yinghao
%A Su, Hanting
%A Kartchner, David
%A Mitchell, Cassie
%A Zhang, Chao
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F ren-etal-2020-denoising
%X We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and incomplete. To address these two challenges, we design a label denoiser, which estimates the source reliability using a conditional soft attention mechanism and then reduces label noise by aggregating rule-annotated weak labels. The denoised pseudo labels then supervise a neural classifier to predicts soft labels for unmatched samples, which address the rule coverage issue. We evaluate our model on five benchmarks for sentiment, topic, and relation classifications. The results show that our model outperforms state-of-the-art weakly-supervised and semi-supervised methods consistently, and achieves comparable performance with fully-supervised methods even without any labeled data. Our code can be found at https://github.com/weakrules/Denoise-multi-weak-sources.
%R 10.18653/v1/2020.findings-emnlp.334
%U https://aclanthology.org/2020.findings-emnlp.334
%U https://doi.org/10.18653/v1/2020.findings-emnlp.334
%P 3739-3754
Markdown (Informal)
[Denoising Multi-Source Weak Supervision for Neural Text Classification](https://aclanthology.org/2020.findings-emnlp.334) (Ren et al., Findings 2020)
ACL