@inproceedings{liu-etal-2021-noisy-labeled,
title = "Noisy-Labeled {NER} with Confidence Estimation",
author = "Liu, Kun and
Fu, Yao and
Tan, Chuanqi and
Chen, Mosha and
Zhang, Ningyu and
Huang, Songfang and
Gao, Sheng",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.269",
doi = "10.18653/v1/2021.naacl-main.269",
pages = "3437--3445",
abstract = "Recent studies in deep learning have shown significant progress in named entity recognition (NER). However, most existing works assume clean data annotation, while real-world scenarios typically involve a large amount of noises from a variety of sources (e.g., pseudo, weak, or distant annotations). This work studies NER under a noisy labeled setting with calibrated confidence estimation. Based on empirical observations of different training dynamics of noisy and clean labels, we propose strategies for estimating confidence scores based on local and global independence assumptions. We partially marginalize out labels of low confidence with a CRF model. We further propose a calibration method for confidence scores based on the structure of entity labels. We integrate our approach into a self-training framework for boosting performance. Experiments in general noisy settings with four languages and distantly labeled settings demonstrate the effectiveness of our method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-noisy-labeled">
<titleInfo>
<title>Noisy-Labeled NER with Confidence Estimation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuanqi</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mosha</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ningyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songfang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Recent studies in deep learning have shown significant progress in named entity recognition (NER). However, most existing works assume clean data annotation, while real-world scenarios typically involve a large amount of noises from a variety of sources (e.g., pseudo, weak, or distant annotations). This work studies NER under a noisy labeled setting with calibrated confidence estimation. Based on empirical observations of different training dynamics of noisy and clean labels, we propose strategies for estimating confidence scores based on local and global independence assumptions. We partially marginalize out labels of low confidence with a CRF model. We further propose a calibration method for confidence scores based on the structure of entity labels. We integrate our approach into a self-training framework for boosting performance. Experiments in general noisy settings with four languages and distantly labeled settings demonstrate the effectiveness of our method.</abstract>
<identifier type="citekey">liu-etal-2021-noisy-labeled</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.269</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.269</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3437</start>
<end>3445</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Noisy-Labeled NER with Confidence Estimation
%A Liu, Kun
%A Fu, Yao
%A Tan, Chuanqi
%A Chen, Mosha
%A Zhang, Ningyu
%A Huang, Songfang
%A Gao, Sheng
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F liu-etal-2021-noisy-labeled
%X Recent studies in deep learning have shown significant progress in named entity recognition (NER). However, most existing works assume clean data annotation, while real-world scenarios typically involve a large amount of noises from a variety of sources (e.g., pseudo, weak, or distant annotations). This work studies NER under a noisy labeled setting with calibrated confidence estimation. Based on empirical observations of different training dynamics of noisy and clean labels, we propose strategies for estimating confidence scores based on local and global independence assumptions. We partially marginalize out labels of low confidence with a CRF model. We further propose a calibration method for confidence scores based on the structure of entity labels. We integrate our approach into a self-training framework for boosting performance. Experiments in general noisy settings with four languages and distantly labeled settings demonstrate the effectiveness of our method.
%R 10.18653/v1/2021.naacl-main.269
%U https://aclanthology.org/2021.naacl-main.269
%U https://doi.org/10.18653/v1/2021.naacl-main.269
%P 3437-3445
Markdown (Informal)
[Noisy-Labeled NER with Confidence Estimation](https://aclanthology.org/2021.naacl-main.269) (Liu et al., NAACL 2021)
ACL
- Kun Liu, Yao Fu, Chuanqi Tan, Mosha Chen, Ningyu Zhang, Songfang Huang, and Sheng Gao. 2021. Noisy-Labeled NER with Confidence Estimation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3437–3445, Online. Association for Computational Linguistics.