@inproceedings{pang-etal-2022-divide,
title = "Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction",
author = "Pang, Kunyuan and
Zhang, Haoyu and
Zhou, Jie and
Wang, Ting",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.141",
doi = "10.18653/v1/2022.acl-long.141",
pages = "1997--2006",
abstract = "Fine-grained Entity Typing (FET) has made great progress based on distant supervision but still suffers from label noise. Existing FET noise learning methods rely on prediction distributions in an instance-independent manner, which causes the problem of confirmation bias. In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems. FCLC first train a coarse backbone model as a feature extractor and noise estimator. Loss correction is then applied to each feature cluster, learning directly from the noisy labels. Experimental results on three public datasets show that FCLC achieves the best performance over existing competitive systems. Auxiliary experiments further demonstrate that FCLC is stable to hyperparameters and it does help mitigate confirmation bias. We also find that in the extreme case of no clean data, the FCLC framework still achieves competitive performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pang-etal-2022-divide">
<titleInfo>
<title>Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kunyuan</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fine-grained Entity Typing (FET) has made great progress based on distant supervision but still suffers from label noise. Existing FET noise learning methods rely on prediction distributions in an instance-independent manner, which causes the problem of confirmation bias. In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems. FCLC first train a coarse backbone model as a feature extractor and noise estimator. Loss correction is then applied to each feature cluster, learning directly from the noisy labels. Experimental results on three public datasets show that FCLC achieves the best performance over existing competitive systems. Auxiliary experiments further demonstrate that FCLC is stable to hyperparameters and it does help mitigate confirmation bias. We also find that in the extreme case of no clean data, the FCLC framework still achieves competitive performance.</abstract>
<identifier type="citekey">pang-etal-2022-divide</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.141</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.141</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1997</start>
<end>2006</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction
%A Pang, Kunyuan
%A Zhang, Haoyu
%A Zhou, Jie
%A Wang, Ting
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F pang-etal-2022-divide
%X Fine-grained Entity Typing (FET) has made great progress based on distant supervision but still suffers from label noise. Existing FET noise learning methods rely on prediction distributions in an instance-independent manner, which causes the problem of confirmation bias. In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems. FCLC first train a coarse backbone model as a feature extractor and noise estimator. Loss correction is then applied to each feature cluster, learning directly from the noisy labels. Experimental results on three public datasets show that FCLC achieves the best performance over existing competitive systems. Auxiliary experiments further demonstrate that FCLC is stable to hyperparameters and it does help mitigate confirmation bias. We also find that in the extreme case of no clean data, the FCLC framework still achieves competitive performance.
%R 10.18653/v1/2022.acl-long.141
%U https://aclanthology.org/2022.acl-long.141
%U https://doi.org/10.18653/v1/2022.acl-long.141
%P 1997-2006
Markdown (Informal)
[Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction](https://aclanthology.org/2022.acl-long.141) (Pang et al., ACL 2022)
ACL