@inproceedings{wong-etal-2021-cross,
title = "Cross-replication Reliability - An Empirical Approach to Interpreting Inter-rater Reliability",
author = "Wong, Ka and
Paritosh, Praveen and
Aroyo, Lora",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.548",
doi = "10.18653/v1/2021.acl-long.548",
pages = "7053--7065",
abstract = "When collecting annotations and labeled data from humans, a standard practice is to use inter-rater reliability (IRR) as a measure of data goodness (Hallgren, 2012). Metrics such as Krippendorff{'}s alpha or Cohen{'}s kappa are typically required to be above a threshold of 0.6 (Landis and Koch, 1977). These absolute thresholds are unreasonable for crowdsourced data from annotators with high cultural and training variances, especially on subjective topics. We present a new alternative to interpreting IRR that is more empirical and contextualized. It is based upon benchmarking IRR against baseline measures in a replication, one of which is a novel cross-replication reliability (xRR) measure based on Cohen{'}s (1960) kappa. We call this approach the xRR framework. We opensource a replication dataset of 4 million human judgements of facial expressions and analyze it with the proposed framework. We argue this framework can be used to measure the quality of crowdsourced datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wong-etal-2021-cross">
<titleInfo>
<title>Cross-replication Reliability - An Empirical Approach to Interpreting Inter-rater Reliability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ka</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Praveen</namePart>
<namePart type="family">Paritosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lora</namePart>
<namePart type="family">Aroyo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>When collecting annotations and labeled data from humans, a standard practice is to use inter-rater reliability (IRR) as a measure of data goodness (Hallgren, 2012). Metrics such as Krippendorff’s alpha or Cohen’s kappa are typically required to be above a threshold of 0.6 (Landis and Koch, 1977). These absolute thresholds are unreasonable for crowdsourced data from annotators with high cultural and training variances, especially on subjective topics. We present a new alternative to interpreting IRR that is more empirical and contextualized. It is based upon benchmarking IRR against baseline measures in a replication, one of which is a novel cross-replication reliability (xRR) measure based on Cohen’s (1960) kappa. We call this approach the xRR framework. We opensource a replication dataset of 4 million human judgements of facial expressions and analyze it with the proposed framework. We argue this framework can be used to measure the quality of crowdsourced datasets.</abstract>
<identifier type="citekey">wong-etal-2021-cross</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.548</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.548</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>7053</start>
<end>7065</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-replication Reliability - An Empirical Approach to Interpreting Inter-rater Reliability
%A Wong, Ka
%A Paritosh, Praveen
%A Aroyo, Lora
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F wong-etal-2021-cross
%X When collecting annotations and labeled data from humans, a standard practice is to use inter-rater reliability (IRR) as a measure of data goodness (Hallgren, 2012). Metrics such as Krippendorff’s alpha or Cohen’s kappa are typically required to be above a threshold of 0.6 (Landis and Koch, 1977). These absolute thresholds are unreasonable for crowdsourced data from annotators with high cultural and training variances, especially on subjective topics. We present a new alternative to interpreting IRR that is more empirical and contextualized. It is based upon benchmarking IRR against baseline measures in a replication, one of which is a novel cross-replication reliability (xRR) measure based on Cohen’s (1960) kappa. We call this approach the xRR framework. We opensource a replication dataset of 4 million human judgements of facial expressions and analyze it with the proposed framework. We argue this framework can be used to measure the quality of crowdsourced datasets.
%R 10.18653/v1/2021.acl-long.548
%U https://aclanthology.org/2021.acl-long.548
%U https://doi.org/10.18653/v1/2021.acl-long.548
%P 7053-7065
Markdown (Informal)
[Cross-replication Reliability - An Empirical Approach to Interpreting Inter-rater Reliability](https://aclanthology.org/2021.acl-long.548) (Wong et al., ACL-IJCNLP 2021)
ACL