<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maeda-etal-2024-decomposing">
    <titleInfo>
        <title>Decomposing Co-occurrence Matrices into Interpretable Components as Formal Concepts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Akihiro</namePart>
        <namePart type="family">Maeda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Takuma</namePart>
        <namePart type="family">Torii</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shohei</namePart>
        <namePart type="family">Hidaka</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</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This study addresses the interpretability of word representations through an investigation of a count-based co-occurrence matrix. Employing the mathematical methodology of Formal Concept Analysis, we reveal an underlying structure that is amenable to human interpretation. Furthermore, we unveil the emergence of hierarchical and geometrical structures within word vectors as consequences of word usage. Our experiments on the PPMI matrix demonstrate that the formal concepts that we identified align with interpretable categories, as shown in the category completion task.</abstract>
    <identifier type="citekey">maeda-etal-2024-decomposing</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-acl.278</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.278</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>4683</start>
            <end>4700</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Decomposing Co-occurrence Matrices into Interpretable Components as Formal Concepts
%A Maeda, Akihiro
%A Torii, Takuma
%A Hidaka, Shohei
%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
%F maeda-etal-2024-decomposing
%X This study addresses the interpretability of word representations through an investigation of a count-based co-occurrence matrix. Employing the mathematical methodology of Formal Concept Analysis, we reveal an underlying structure that is amenable to human interpretation. Furthermore, we unveil the emergence of hierarchical and geometrical structures within word vectors as consequences of word usage. Our experiments on the PPMI matrix demonstrate that the formal concepts that we identified align with interpretable categories, as shown in the category completion task.
%R 10.18653/v1/2024.findings-acl.278
%U https://aclanthology.org/2024.findings-acl.278
%U https://doi.org/10.18653/v1/2024.findings-acl.278
%P 4683-4700

Markdown (Informal)

[Decomposing Co-occurrence Matrices into Interpretable Components as Formal Concepts](https://aclanthology.org/2024.findings-acl.278) (Maeda et al., Findings 2024)

• Decomposing Co-occurrence Matrices into Interpretable Components as Formal Concepts (Maeda et al., Findings 2024)

ACL

• Akihiro Maeda, Takuma Torii, and Shohei Hidaka. 2024. Decomposing Co-occurrence Matrices into Interpretable Components as Formal Concepts. In Findings of the Association for Computational Linguistics: ACL 2024, pages 4683–4700, Bangkok, Thailand. Association for Computational Linguistics.