@inproceedings{liu-etal-2022-noise,
title = "Noise Learning for Text Classification: A Benchmark",
author = "Liu, Bo and
Xu, Wandi and
Xiang, Yuejia and
Wu, Xiaojun and
He, Lejian and
Zhang, Bowen and
Zhu, Li",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.402",
pages = "4557--4567",
abstract = "Noise Learning is important in the task of text classification which depends on massive labeled data that could be error-prone. However, we find that noise learning in text classification is relatively underdeveloped: 1. many methods that have been proven effective in the image domain are not explored in text classification, 2. it is difficult to conduct a fair comparison between previous studies as they do experiments in different noise settings. In this work, we adapt four state-of-the-art methods of noise learning from the image domain to text classification. Moreover, we conduct comprehensive experiments on our benchmark of noise learning with seven commonly-used methods, four datasets, and five noise modes. Additionally, most previous works are based on an implicit hypothesis that the commonly-used datasets such as TREC, Ag-News and Chnsenticorp contain no errors. However, these datasets indeed contain 0.61{\%} to 15.77{\%} noise labels which we define as intrinsic noise that can cause inaccurate evaluation. Therefore, we build a new dataset Golden-Chnsenticorp( G-Chnsenticorp) without intrinsic noise to more accurately compare the effects of different noise learning methods. To the best of our knowledge, this is the first benchmark of noise learning for text classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-noise">
<titleInfo>
<title>Noise Learning for Text Classification: A Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wandi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuejia</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lejian</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Noise Learning is important in the task of text classification which depends on massive labeled data that could be error-prone. However, we find that noise learning in text classification is relatively underdeveloped: 1. many methods that have been proven effective in the image domain are not explored in text classification, 2. it is difficult to conduct a fair comparison between previous studies as they do experiments in different noise settings. In this work, we adapt four state-of-the-art methods of noise learning from the image domain to text classification. Moreover, we conduct comprehensive experiments on our benchmark of noise learning with seven commonly-used methods, four datasets, and five noise modes. Additionally, most previous works are based on an implicit hypothesis that the commonly-used datasets such as TREC, Ag-News and Chnsenticorp contain no errors. However, these datasets indeed contain 0.61% to 15.77% noise labels which we define as intrinsic noise that can cause inaccurate evaluation. Therefore, we build a new dataset Golden-Chnsenticorp( G-Chnsenticorp) without intrinsic noise to more accurately compare the effects of different noise learning methods. To the best of our knowledge, this is the first benchmark of noise learning for text classification.</abstract>
<identifier type="citekey">liu-etal-2022-noise</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.402</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4557</start>
<end>4567</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Noise Learning for Text Classification: A Benchmark
%A Liu, Bo
%A Xu, Wandi
%A Xiang, Yuejia
%A Wu, Xiaojun
%A He, Lejian
%A Zhang, Bowen
%A Zhu, Li
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F liu-etal-2022-noise
%X Noise Learning is important in the task of text classification which depends on massive labeled data that could be error-prone. However, we find that noise learning in text classification is relatively underdeveloped: 1. many methods that have been proven effective in the image domain are not explored in text classification, 2. it is difficult to conduct a fair comparison between previous studies as they do experiments in different noise settings. In this work, we adapt four state-of-the-art methods of noise learning from the image domain to text classification. Moreover, we conduct comprehensive experiments on our benchmark of noise learning with seven commonly-used methods, four datasets, and five noise modes. Additionally, most previous works are based on an implicit hypothesis that the commonly-used datasets such as TREC, Ag-News and Chnsenticorp contain no errors. However, these datasets indeed contain 0.61% to 15.77% noise labels which we define as intrinsic noise that can cause inaccurate evaluation. Therefore, we build a new dataset Golden-Chnsenticorp( G-Chnsenticorp) without intrinsic noise to more accurately compare the effects of different noise learning methods. To the best of our knowledge, this is the first benchmark of noise learning for text classification.
%U https://aclanthology.org/2022.coling-1.402
%P 4557-4567
Markdown (Informal)
[Noise Learning for Text Classification: A Benchmark](https://aclanthology.org/2022.coling-1.402) (Liu et al., COLING 2022)
ACL
- Bo Liu, Wandi Xu, Yuejia Xiang, Xiaojun Wu, Lejian He, Bowen Zhang, and Li Zhu. 2022. Noise Learning for Text Classification: A Benchmark. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4557–4567, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.