@inproceedings{james-2026-counting,
title = "Counting on Consensus: Selecting the Right Inter-Annotator Agreement Metric for {NLP} Annotation and Evaluation",
author = "James, Joseph H. F.",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.347/",
doi = "10.63317/2wuxteb6uvcj",
pages = "4434--4446",
abstract = "Human annotation remains the foundation of reliable and interpretable data in Natural Language Processing (NLP). As annotation and evaluation tasks continue to expand, from categorical labelling to segmentation, subjective judgment, and continuous rating, measuring agreement between annotators has become increasingly more complex. This paper outlines how inter-annotator agreement (IAA) has been conceptualised and applied across NLP and related disciplines, describing the assumptions and limitations of common approaches. We organise agreement measures by task type and discuss how factors such as label imbalance and missing data influence reliability estimates. In addition, we highlight best practices for clear and transparent reporting, including the use of confidence intervals and the analysis of disagreement patterns. The paper aims to serve as a guide for selecting and interpreting agreement measures, promoting more consistent and reproducible human annotation and evaluation in NLP."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="james-2026-counting">
<titleInfo>
<title>Counting on Consensus: Selecting the Right Inter-Annotator Agreement Metric for NLP Annotation and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="given">H</namePart>
<namePart type="given">F</namePart>
<namePart type="family">James</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Human annotation remains the foundation of reliable and interpretable data in Natural Language Processing (NLP). As annotation and evaluation tasks continue to expand, from categorical labelling to segmentation, subjective judgment, and continuous rating, measuring agreement between annotators has become increasingly more complex. This paper outlines how inter-annotator agreement (IAA) has been conceptualised and applied across NLP and related disciplines, describing the assumptions and limitations of common approaches. We organise agreement measures by task type and discuss how factors such as label imbalance and missing data influence reliability estimates. In addition, we highlight best practices for clear and transparent reporting, including the use of confidence intervals and the analysis of disagreement patterns. The paper aims to serve as a guide for selecting and interpreting agreement measures, promoting more consistent and reproducible human annotation and evaluation in NLP.</abstract>
<identifier type="citekey">james-2026-counting</identifier>
<identifier type="doi">10.63317/2wuxteb6uvcj</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.347/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4434</start>
<end>4446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Counting on Consensus: Selecting the Right Inter-Annotator Agreement Metric for NLP Annotation and Evaluation
%A James, Joseph H. F.
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F james-2026-counting
%X Human annotation remains the foundation of reliable and interpretable data in Natural Language Processing (NLP). As annotation and evaluation tasks continue to expand, from categorical labelling to segmentation, subjective judgment, and continuous rating, measuring agreement between annotators has become increasingly more complex. This paper outlines how inter-annotator agreement (IAA) has been conceptualised and applied across NLP and related disciplines, describing the assumptions and limitations of common approaches. We organise agreement measures by task type and discuss how factors such as label imbalance and missing data influence reliability estimates. In addition, we highlight best practices for clear and transparent reporting, including the use of confidence intervals and the analysis of disagreement patterns. The paper aims to serve as a guide for selecting and interpreting agreement measures, promoting more consistent and reproducible human annotation and evaluation in NLP.
%R 10.63317/2wuxteb6uvcj
%U https://aclanthology.org/2026.lrec-1.347/
%U https://doi.org/10.63317/2wuxteb6uvcj
%P 4434-4446
Markdown (Informal)
[Counting on Consensus: Selecting the Right Inter-Annotator Agreement Metric for NLP Annotation and Evaluation](https://aclanthology.org/2026.lrec-1.347/) (James, LREC 2026)
ACL