<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vitsakis-etal-2024-voices">
    <titleInfo>
        <title>Voices in a Crowd: Searching for clusters of unique perspectives</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nikolas</namePart>
        <namePart type="family">Vitsakis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amit</namePart>
        <namePart type="family">Parekh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ioannis</namePart>
        <namePart type="family">Konstas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Language models have been shown to reproduce underlying biases existing in their training data, which is the majority perspective by default. Proposed solutions aim to capture minority perspectives by either modelling annotator disagreements or grouping annotators based on shared metadata, both of which face significant challenges. We propose a framework that trains models without encoding annotator metadata, extracts latent embeddings informed by annotator behaviour, and creates clusters of similar opinions, that we refer to as voices. Resulting clusters are validated post-hoc via internal and external quantitative metrics, as well a qualitative analysis to identify the type of voice that each cluster represents. Our results demonstrate the strong generalisation capability of our framework, indicated by resulting clusters being adequately robust, while also capturing minority perspectives based on different demographic factors throughout two distinct datasets.</abstract>
    <identifier type="citekey">vitsakis-etal-2024-voices</identifier>
    <identifier type="doi">10.18653/v1/2024.emnlp-main.696</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.696/</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>12517</start>
            <end>12539</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Voices in a Crowd: Searching for clusters of unique perspectives
%A Vitsakis, Nikolas
%A Parekh, Amit
%A Konstas, Ioannis
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F vitsakis-etal-2024-voices
%X Language models have been shown to reproduce underlying biases existing in their training data, which is the majority perspective by default. Proposed solutions aim to capture minority perspectives by either modelling annotator disagreements or grouping annotators based on shared metadata, both of which face significant challenges. We propose a framework that trains models without encoding annotator metadata, extracts latent embeddings informed by annotator behaviour, and creates clusters of similar opinions, that we refer to as voices. Resulting clusters are validated post-hoc via internal and external quantitative metrics, as well a qualitative analysis to identify the type of voice that each cluster represents. Our results demonstrate the strong generalisation capability of our framework, indicated by resulting clusters being adequately robust, while also capturing minority perspectives based on different demographic factors throughout two distinct datasets.
%R 10.18653/v1/2024.emnlp-main.696
%U https://aclanthology.org/2024.emnlp-main.696/
%U https://doi.org/10.18653/v1/2024.emnlp-main.696
%P 12517-12539

Markdown (Informal)

[Voices in a Crowd: Searching for clusters of unique perspectives](https://aclanthology.org/2024.emnlp-main.696/) (Vitsakis et al., EMNLP 2024)

• Voices in a Crowd: Searching for clusters of unique perspectives (Vitsakis et al., EMNLP 2024)

ACL

• Nikolas Vitsakis, Amit Parekh, and Ioannis Konstas. 2024. Voices in a Crowd: Searching for clusters of unique perspectives. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12517–12539, Miami, Florida, USA. Association for Computational Linguistics.