@inproceedings{wu-etal-2024-modelling,
title = "Modelling Variability in Human Annotator Simulation",
author = "Wu, Wen and
Chen, Wenlin and
Zhang, Chao and
Woodland, Phil",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.67",
pages = "1139--1157",
abstract = "Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation tasks such as data annotation and system assessment. It is important to incorporate the variability present in human evaluation into HAS, since it helps capture diverse subjective interpretations and mitigate potential biases and over-representation. This work introduces a novel framework for modelling variability in HAS. Conditional softmax flow (S-CNF) is proposed to model the distribution of subjective human annotations, which leverages diverse human annotations via meta-learning. This enables efficient generation of annotations that exhibit human variability for unlabelled input. In addition, a wide range of evaluation metrics are adopted to assess the capability and efficiency of HAS systems in predicting the aggregated behaviours of human annotators, matching the distribution of human annotations, and simulating the inter-annotator disagreements. Results demonstrate that the proposed method achieves state-of-the-art performance on two real-world human evaluation tasks: emotion recognition and toxic speech detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-modelling">
<titleInfo>
<title>Modelling Variability in Human Annotator Simulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenlin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Woodland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation tasks such as data annotation and system assessment. It is important to incorporate the variability present in human evaluation into HAS, since it helps capture diverse subjective interpretations and mitigate potential biases and over-representation. This work introduces a novel framework for modelling variability in HAS. Conditional softmax flow (S-CNF) is proposed to model the distribution of subjective human annotations, which leverages diverse human annotations via meta-learning. This enables efficient generation of annotations that exhibit human variability for unlabelled input. In addition, a wide range of evaluation metrics are adopted to assess the capability and efficiency of HAS systems in predicting the aggregated behaviours of human annotators, matching the distribution of human annotations, and simulating the inter-annotator disagreements. Results demonstrate that the proposed method achieves state-of-the-art performance on two real-world human evaluation tasks: emotion recognition and toxic speech detection.</abstract>
<identifier type="citekey">wu-etal-2024-modelling</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.67</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>1139</start>
<end>1157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modelling Variability in Human Annotator Simulation
%A Wu, Wen
%A Chen, Wenlin
%A Zhang, Chao
%A Woodland, Phil
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F wu-etal-2024-modelling
%X Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation tasks such as data annotation and system assessment. It is important to incorporate the variability present in human evaluation into HAS, since it helps capture diverse subjective interpretations and mitigate potential biases and over-representation. This work introduces a novel framework for modelling variability in HAS. Conditional softmax flow (S-CNF) is proposed to model the distribution of subjective human annotations, which leverages diverse human annotations via meta-learning. This enables efficient generation of annotations that exhibit human variability for unlabelled input. In addition, a wide range of evaluation metrics are adopted to assess the capability and efficiency of HAS systems in predicting the aggregated behaviours of human annotators, matching the distribution of human annotations, and simulating the inter-annotator disagreements. Results demonstrate that the proposed method achieves state-of-the-art performance on two real-world human evaluation tasks: emotion recognition and toxic speech detection.
%U https://aclanthology.org/2024.findings-acl.67
%P 1139-1157
Markdown (Informal)
[Modelling Variability in Human Annotator Simulation](https://aclanthology.org/2024.findings-acl.67) (Wu et al., Findings 2024)
ACL
- Wen Wu, Wenlin Chen, Chao Zhang, and Phil Woodland. 2024. Modelling Variability in Human Annotator Simulation. In Findings of the Association for Computational Linguistics ACL 2024, pages 1139–1157, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.