<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-difference">
    <titleInfo>
        <title>On the Difference of BERT-style and CLIP-style Text Encoders</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhihong</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guiming</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shizhe</namePart>
        <namePart type="family">Diao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiang</namePart>
        <namePart type="family">Wan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benyou</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Masked language modeling (MLM) has been one of the most popular pretraining recipes in natural language processing, e.g., BERT, one of the representative models. Recently, contrastive language-image pretraining (CLIP) has also attracted attention, especially its vision models that achieve excellent performance on a broad range of vision tasks. However, few studies are dedicated to studying the text encoders learned by CLIP. In this paper, we analyze the difference between BERT-style and CLIP-style text encoders from three experiments: (i) general text understanding, (ii) vision-centric text understanding, and (iii) text-to-image generation. Experimental analyses show that although CLIP-style text encoders underperform BERT-style ones for general text understanding tasks, they are equipped with a unique ability, i.e., synesthesia, for the cross-modal association, which is more similar to the senses of humans.</abstract>
    <identifier type="citekey">chen-etal-2023-difference</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.866</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.866</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>13710</start>
            <end>13721</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On the Difference of BERT-style and CLIP-style Text Encoders
%A Chen, Zhihong
%A Chen, Guiming
%A Diao, Shizhe
%A Wan, Xiang
%A Wang, Benyou
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chen-etal-2023-difference
%X Masked language modeling (MLM) has been one of the most popular pretraining recipes in natural language processing, e.g., BERT, one of the representative models. Recently, contrastive language-image pretraining (CLIP) has also attracted attention, especially its vision models that achieve excellent performance on a broad range of vision tasks. However, few studies are dedicated to studying the text encoders learned by CLIP. In this paper, we analyze the difference between BERT-style and CLIP-style text encoders from three experiments: (i) general text understanding, (ii) vision-centric text understanding, and (iii) text-to-image generation. Experimental analyses show that although CLIP-style text encoders underperform BERT-style ones for general text understanding tasks, they are equipped with a unique ability, i.e., synesthesia, for the cross-modal association, which is more similar to the senses of humans.
%R 10.18653/v1/2023.findings-acl.866
%U https://aclanthology.org/2023.findings-acl.866
%U https://doi.org/10.18653/v1/2023.findings-acl.866
%P 13710-13721

Markdown (Informal)

[On the Difference of BERT-style and CLIP-style Text Encoders](https://aclanthology.org/2023.findings-acl.866) (Chen et al., Findings 2023)

• On the Difference of BERT-style and CLIP-style Text Encoders (Chen et al., Findings 2023)

ACL

• Zhihong Chen, Guiming Chen, Shizhe Diao, Xiang Wan, and Benyou Wang. 2023. On the Difference of BERT-style and CLIP-style Text Encoders. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13710–13721, Toronto, Canada. Association for Computational Linguistics.