<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parcalabescu-2025-measuring">
    <titleInfo>
        <title>Measuring the Contributions of Vision and Text Modalities</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Letitia</namePart>
        <namePart type="family">Parcalabescu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-02</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Journal for Language Technology and Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>German Society for Computational Linguistics and Language Technology</publisher>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>This dissertation investigates multimodal transformers that process both image and text modalities together to generate outputs for various tasks (such as answering questions about images). Specifically, methods are developed to assess the effectiveness of vision and language models in combining, understanding, utilizing, and explaining information from these two modalities. The dissertation contributes to the advancement of the field in three ways: (i) by measuring specific and task-independent capabilities of vision and language models, (ii) by interpreting these models to quantify the extent to which they use and integrate information from both modalities, and (iii) by evaluating their ability to provide self-consistent explanations of their outputs to users.</abstract>
    <identifier type="citekey">parcalabescu-2025-measuring</identifier>
    <identifier type="doi">10.21248/jlcl.38.2025.261</identifier>
    <location>
        <url>https://aclanthology.org/2025.jlcl-1.1/</url>
    </location>
    <part>
        <date>2025-02</date>
        <detail type="volume"><number>38</number></detail>
        <detail type="issue"><number>1</number></detail>
        <extent unit="page">
            <start>1</start>
            <end>3</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Measuring the Contributions of Vision and Text Modalities
%A Parcalabescu, Letitia
%J Journal for Language Technology and Computational Linguistics
%D 2025
%8 February
%V 38
%N 1
%I German Society for Computational Linguistics and Language Technology
%F parcalabescu-2025-measuring
%X This dissertation investigates multimodal transformers that process both image and text modalities together to generate outputs for various tasks (such as answering questions about images). Specifically, methods are developed to assess the effectiveness of vision and language models in combining, understanding, utilizing, and explaining information from these two modalities. The dissertation contributes to the advancement of the field in three ways: (i) by measuring specific and task-independent capabilities of vision and language models, (ii) by interpreting these models to quantify the extent to which they use and integrate information from both modalities, and (iii) by evaluating their ability to provide self-consistent explanations of their outputs to users.
%R 10.21248/jlcl.38.2025.261
%U https://aclanthology.org/2025.jlcl-1.1/
%U https://doi.org/10.21248/jlcl.38.2025.261
%P 1-3

Markdown (Informal)

[Measuring the Contributions of Vision and Text Modalities](https://aclanthology.org/2025.jlcl-1.1/) (Parcalabescu, JLCL 2025)

• Measuring the Contributions of Vision and Text Modalities (Parcalabescu, JLCL 2025)

ACL

• Letitia Parcalabescu. 2025. Measuring the Contributions of Vision and Text Modalities. Journal for Language Technology and Computational Linguistics, 38(1):1–3.