<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ogezi-etal-2024-semantically">
    <titleInfo>
        <title>Semantically-Prompted Language Models Improve Visual Descriptions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Ogezi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bradley</namePart>
        <namePart type="family">Hauer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Grzegorz</namePart>
        <namePart type="family">Kondrak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Language-vision models like CLIP have made significant strides in vision tasks, such as zero-shot image classification (ZSIC). However, generating specific and expressive visual descriptions remains challenging; descriptions produced by current methods are often ambiguous and lacking in granularity. To tackle these issues, we propose V-GLOSS: Visual Glosses, a novel method built upon two key ideas. The first is Semantic Prompting, which conditions a language model on structured semantic knowledge. The second is a new contrastive algorithm that elicits fine-grained distinctions between similar concepts. With both ideas, we demonstrate that V-GLOSS improves visual descriptions and achieves strong results in the zero-shot setting on general and fine-grained image-classification datasets, including ImageNet, STL-10, FGVC Aircraft, and Flowers 102. Moreover, these descriptive capabilities contribute to enhancing image-generation performance. Finally, we introduce a quality-tested silver dataset with descriptions generated with V-GLOSS for all ImageNet classes.</abstract>
    <identifier type="citekey">ogezi-etal-2024-semantically</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-naacl.267</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-naacl.267</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>4285</start>
            <end>4302</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Semantically-Prompted Language Models Improve Visual Descriptions
%A Ogezi, Michael
%A Hauer, Bradley
%A Kondrak, Grzegorz
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F ogezi-etal-2024-semantically
%X Language-vision models like CLIP have made significant strides in vision tasks, such as zero-shot image classification (ZSIC). However, generating specific and expressive visual descriptions remains challenging; descriptions produced by current methods are often ambiguous and lacking in granularity. To tackle these issues, we propose V-GLOSS: Visual Glosses, a novel method built upon two key ideas. The first is Semantic Prompting, which conditions a language model on structured semantic knowledge. The second is a new contrastive algorithm that elicits fine-grained distinctions between similar concepts. With both ideas, we demonstrate that V-GLOSS improves visual descriptions and achieves strong results in the zero-shot setting on general and fine-grained image-classification datasets, including ImageNet, STL-10, FGVC Aircraft, and Flowers 102. Moreover, these descriptive capabilities contribute to enhancing image-generation performance. Finally, we introduce a quality-tested silver dataset with descriptions generated with V-GLOSS for all ImageNet classes.
%R 10.18653/v1/2024.findings-naacl.267
%U https://aclanthology.org/2024.findings-naacl.267
%U https://doi.org/10.18653/v1/2024.findings-naacl.267
%P 4285-4302

Markdown (Informal)

[Semantically-Prompted Language Models Improve Visual Descriptions](https://aclanthology.org/2024.findings-naacl.267) (Ogezi et al., Findings 2024)

• Semantically-Prompted Language Models Improve Visual Descriptions (Ogezi et al., Findings 2024)

ACL

• Michael Ogezi, Bradley Hauer, and Grzegorz Kondrak. 2024. Semantically-Prompted Language Models Improve Visual Descriptions. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 4285–4302, Mexico City, Mexico. Association for Computational Linguistics.