@inproceedings{deng-etal-2023-annotate,
title = "You Are What You Annotate: Towards Better Models through Annotator Representations",
author = "Deng, Naihao and
Zhang, Xinliang and
Liu, Siyang and
Wu, Winston and
Wang, Lu and
Mihalcea, Rada",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.832",
doi = "10.18653/v1/2023.findings-emnlp.832",
pages = "12475--12498",
abstract = "Annotator disagreement is ubiquitous in natural language processing (NLP) tasks. There are multiple reasons for such disagreements, including the subjectivity of the task, difficult cases, unclear guidelines, and so on. Rather than simply aggregating labels to obtain data annotations, we instead try to directly model the diverse perspectives of the annotators, and explicitly account for annotators{'} idiosyncrasies in the modeling process by creating representations for each annotator (*annotator embeddings*) and also their annotations (*annotation embeddings*). In addition, we propose **TID-8**, **T**he **I**nherent **D**isagreement - **8** dataset, a benchmark that consists of eight existing language understanding datasets that have inherent annotator disagreement. We test our approach on TID-8 and show that our approach helps models learn significantly better from disagreements on six different datasets in TID-8 while increasing model size by fewer than 1{\%} parameters. By capturing the unique tendencies and subjectivity of individual annotators through embeddings, our representations prime AI models to be inclusive of diverse viewpoints.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deng-etal-2023-annotate">
<titleInfo>
<title>You Are What You Annotate: Towards Better Models through Annotator Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naihao</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinliang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Winston</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Annotator disagreement is ubiquitous in natural language processing (NLP) tasks. There are multiple reasons for such disagreements, including the subjectivity of the task, difficult cases, unclear guidelines, and so on. Rather than simply aggregating labels to obtain data annotations, we instead try to directly model the diverse perspectives of the annotators, and explicitly account for annotators’ idiosyncrasies in the modeling process by creating representations for each annotator (*annotator embeddings*) and also their annotations (*annotation embeddings*). In addition, we propose **TID-8**, **T**he **I**nherent **D**isagreement - **8** dataset, a benchmark that consists of eight existing language understanding datasets that have inherent annotator disagreement. We test our approach on TID-8 and show that our approach helps models learn significantly better from disagreements on six different datasets in TID-8 while increasing model size by fewer than 1% parameters. By capturing the unique tendencies and subjectivity of individual annotators through embeddings, our representations prime AI models to be inclusive of diverse viewpoints.</abstract>
<identifier type="citekey">deng-etal-2023-annotate</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.832</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.832</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12475</start>
<end>12498</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T You Are What You Annotate: Towards Better Models through Annotator Representations
%A Deng, Naihao
%A Zhang, Xinliang
%A Liu, Siyang
%A Wu, Winston
%A Wang, Lu
%A Mihalcea, Rada
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F deng-etal-2023-annotate
%X Annotator disagreement is ubiquitous in natural language processing (NLP) tasks. There are multiple reasons for such disagreements, including the subjectivity of the task, difficult cases, unclear guidelines, and so on. Rather than simply aggregating labels to obtain data annotations, we instead try to directly model the diverse perspectives of the annotators, and explicitly account for annotators’ idiosyncrasies in the modeling process by creating representations for each annotator (*annotator embeddings*) and also their annotations (*annotation embeddings*). In addition, we propose **TID-8**, **T**he **I**nherent **D**isagreement - **8** dataset, a benchmark that consists of eight existing language understanding datasets that have inherent annotator disagreement. We test our approach on TID-8 and show that our approach helps models learn significantly better from disagreements on six different datasets in TID-8 while increasing model size by fewer than 1% parameters. By capturing the unique tendencies and subjectivity of individual annotators through embeddings, our representations prime AI models to be inclusive of diverse viewpoints.
%R 10.18653/v1/2023.findings-emnlp.832
%U https://aclanthology.org/2023.findings-emnlp.832
%U https://doi.org/10.18653/v1/2023.findings-emnlp.832
%P 12475-12498
Markdown (Informal)
[You Are What You Annotate: Towards Better Models through Annotator Representations](https://aclanthology.org/2023.findings-emnlp.832) (Deng et al., Findings 2023)
ACL