@inproceedings{desmond-etal-2020-label,
title = "Label Noise in Context",
author = "Desmond, Michael and
Finegan-Dollak, Catherine and
Boston, Jeff and
Arnold, Matt",
editor = "Celikyilmaz, Asli and
Wen, Tsung-Hsien",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-demos.21",
doi = "10.18653/v1/2020.acl-demos.21",
pages = "157--186",
abstract = "Label noise{---}incorrectly or ambiguously labeled training examples{---}can negatively impact model performance. Although noise detection techniques have been around for decades, practitioners rarely apply them, as manual noise remediation is a tedious process. Examples incorrectly flagged as noise waste reviewers{'} time, and correcting label noise without guidance can be difficult. We propose LNIC, a noise-detection method that uses an example{'}s neighborhood within the training set to (a) reduce false positives and (b) provide an explanation as to why the ex- ample was flagged as noise. We demonstrate on several short-text classification datasets that LNIC outperforms the state of the art on measures of precision and F0.5-score. We also show how LNIC{'}s training set context helps a reviewer to understand and correct label noise in a dataset. The LNIC tool lowers the barriers to label noise remediation, increasing its utility for NLP practitioners.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="desmond-etal-2020-label">
<titleInfo>
<title>Label Noise in Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Desmond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Finegan-Dollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeff</namePart>
<namePart type="family">Boston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Arnold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</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>Label noise—incorrectly or ambiguously labeled training examples—can negatively impact model performance. Although noise detection techniques have been around for decades, practitioners rarely apply them, as manual noise remediation is a tedious process. Examples incorrectly flagged as noise waste reviewers’ time, and correcting label noise without guidance can be difficult. We propose LNIC, a noise-detection method that uses an example’s neighborhood within the training set to (a) reduce false positives and (b) provide an explanation as to why the ex- ample was flagged as noise. We demonstrate on several short-text classification datasets that LNIC outperforms the state of the art on measures of precision and F0.5-score. We also show how LNIC’s training set context helps a reviewer to understand and correct label noise in a dataset. The LNIC tool lowers the barriers to label noise remediation, increasing its utility for NLP practitioners.</abstract>
<identifier type="citekey">desmond-etal-2020-label</identifier>
<identifier type="doi">10.18653/v1/2020.acl-demos.21</identifier>
<location>
<url>https://aclanthology.org/2020.acl-demos.21</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>157</start>
<end>186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Label Noise in Context
%A Desmond, Michael
%A Finegan-Dollak, Catherine
%A Boston, Jeff
%A Arnold, Matt
%Y Celikyilmaz, Asli
%Y Wen, Tsung-Hsien
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F desmond-etal-2020-label
%X Label noise—incorrectly or ambiguously labeled training examples—can negatively impact model performance. Although noise detection techniques have been around for decades, practitioners rarely apply them, as manual noise remediation is a tedious process. Examples incorrectly flagged as noise waste reviewers’ time, and correcting label noise without guidance can be difficult. We propose LNIC, a noise-detection method that uses an example’s neighborhood within the training set to (a) reduce false positives and (b) provide an explanation as to why the ex- ample was flagged as noise. We demonstrate on several short-text classification datasets that LNIC outperforms the state of the art on measures of precision and F0.5-score. We also show how LNIC’s training set context helps a reviewer to understand and correct label noise in a dataset. The LNIC tool lowers the barriers to label noise remediation, increasing its utility for NLP practitioners.
%R 10.18653/v1/2020.acl-demos.21
%U https://aclanthology.org/2020.acl-demos.21
%U https://doi.org/10.18653/v1/2020.acl-demos.21
%P 157-186
Markdown (Informal)
[Label Noise in Context](https://aclanthology.org/2020.acl-demos.21) (Desmond et al., ACL 2020)
ACL
- Michael Desmond, Catherine Finegan-Dollak, Jeff Boston, and Matt Arnold. 2020. Label Noise in Context. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 157–186, Online. Association for Computational Linguistics.