@inproceedings{marchal-etal-2022-establishing,
title = "Establishing Annotation Quality in Multi-label Annotations",
author = "Marchal, Marian and
Scholman, Merel and
Yung, Frances and
Demberg, Vera",
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-1.322",
pages = "3659--3668",
abstract = "In many linguistic fields requiring annotated data, multiple interpretations of a single item are possible. Multi-label annotations more accurately reflect this possibility. However, allowing for multi-label annotations also affects the chance that two coders agree with each other. Calculating inter-coder agreement for multi-label datasets is therefore not trivial. In the current contribution, we evaluate different metrics for calculating agreement on multi-label annotations: agreement on the intersection of annotated labels, an augmented version of Cohen{'}s Kappa, and precision, recall and F1. We propose a bootstrapping method to obtain chance agreement for each measure, which allows us to obtain an adjusted agreement coefficient that is more interpretable. We demonstrate how various measures affect estimates of agreement on simulated datasets and present a case study of discourse relation annotations. We also show how the proportion of double labels, and the entropy of the label distribution, influences the measures outlined above and how a bootstrapped adjusted agreement can make agreement measures more comparable across datasets in multi-label scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marchal-etal-2022-establishing">
<titleInfo>
<title>Establishing Annotation Quality in Multi-label Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marian</namePart>
<namePart type="family">Marchal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Merel</namePart>
<namePart type="family">Scholman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frances</namePart>
<namePart type="family">Yung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</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>In many linguistic fields requiring annotated data, multiple interpretations of a single item are possible. Multi-label annotations more accurately reflect this possibility. However, allowing for multi-label annotations also affects the chance that two coders agree with each other. Calculating inter-coder agreement for multi-label datasets is therefore not trivial. In the current contribution, we evaluate different metrics for calculating agreement on multi-label annotations: agreement on the intersection of annotated labels, an augmented version of Cohen’s Kappa, and precision, recall and F1. We propose a bootstrapping method to obtain chance agreement for each measure, which allows us to obtain an adjusted agreement coefficient that is more interpretable. We demonstrate how various measures affect estimates of agreement on simulated datasets and present a case study of discourse relation annotations. We also show how the proportion of double labels, and the entropy of the label distribution, influences the measures outlined above and how a bootstrapped adjusted agreement can make agreement measures more comparable across datasets in multi-label scenarios.</abstract>
<identifier type="citekey">marchal-etal-2022-establishing</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.322</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3659</start>
<end>3668</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Establishing Annotation Quality in Multi-label Annotations
%A Marchal, Marian
%A Scholman, Merel
%A Yung, Frances
%A Demberg, Vera
%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 marchal-etal-2022-establishing
%X In many linguistic fields requiring annotated data, multiple interpretations of a single item are possible. Multi-label annotations more accurately reflect this possibility. However, allowing for multi-label annotations also affects the chance that two coders agree with each other. Calculating inter-coder agreement for multi-label datasets is therefore not trivial. In the current contribution, we evaluate different metrics for calculating agreement on multi-label annotations: agreement on the intersection of annotated labels, an augmented version of Cohen’s Kappa, and precision, recall and F1. We propose a bootstrapping method to obtain chance agreement for each measure, which allows us to obtain an adjusted agreement coefficient that is more interpretable. We demonstrate how various measures affect estimates of agreement on simulated datasets and present a case study of discourse relation annotations. We also show how the proportion of double labels, and the entropy of the label distribution, influences the measures outlined above and how a bootstrapped adjusted agreement can make agreement measures more comparable across datasets in multi-label scenarios.
%U https://aclanthology.org/2022.coling-1.322
%P 3659-3668
Markdown (Informal)
[Establishing Annotation Quality in Multi-label Annotations](https://aclanthology.org/2022.coling-1.322) (Marchal et al., COLING 2022)
ACL
- Marian Marchal, Merel Scholman, Frances Yung, and Vera Demberg. 2022. Establishing Annotation Quality in Multi-label Annotations. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3659–3668, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.