<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mickus-etal-2022-dissect">
    <titleInfo>
        <title>How to Dissect a Muppet: The Structure of Transformer Embedding Spaces</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Timothee</namePart>
        <namePart type="family">Mickus</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Denis</namePart>
        <namePart type="family">Paperno</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mathieu</namePart>
        <namePart type="family">Constant</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Pretrained embeddings based on the Transformer architecture have taken the NLP community by storm. We show that they can mathematically be reframed as a sum of vector factors and showcase how to use this reframing to study the impact of each component. We provide evidence that multi-head attentions and feed-forwards are not equally useful in all downstream applications, as well as a quantitative overview of the effects of finetuning on the overall embedding space. This approach allows us to draw connections to a wide range of previous studies, from vector space anisotropy to attention weights.</abstract>
    <identifier type="citekey">mickus-etal-2022-dissect</identifier>
    <identifier type="doi">10.1162/tacl_a_00501</identifier>
    <location>
        <url>https://aclanthology.org/2022.tacl-1.57</url>
    </location>
    <part>
        <date>2022</date>
        <detail type="volume"><number>10</number></detail>
        <extent unit="page">
            <start>981</start>
            <end>996</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T How to Dissect a Muppet: The Structure of Transformer Embedding Spaces
%A Mickus, Timothee
%A Paperno, Denis
%A Constant, Mathieu
%J Transactions of the Association for Computational Linguistics
%D 2022
%V 10
%I MIT Press
%C Cambridge, MA
%F mickus-etal-2022-dissect
%X Pretrained embeddings based on the Transformer architecture have taken the NLP community by storm. We show that they can mathematically be reframed as a sum of vector factors and showcase how to use this reframing to study the impact of each component. We provide evidence that multi-head attentions and feed-forwards are not equally useful in all downstream applications, as well as a quantitative overview of the effects of finetuning on the overall embedding space. This approach allows us to draw connections to a wide range of previous studies, from vector space anisotropy to attention weights.
%R 10.1162/tacl_a_00501
%U https://aclanthology.org/2022.tacl-1.57
%U https://doi.org/10.1162/tacl_a_00501
%P 981-996

Markdown (Informal)

[How to Dissect a Muppet: The Structure of Transformer Embedding Spaces](https://aclanthology.org/2022.tacl-1.57) (Mickus et al., TACL 2022)

• How to Dissect a Muppet: The Structure of Transformer Embedding Spaces (Mickus et al., TACL 2022)

ACL

• Timothee Mickus, Denis Paperno, and Mathieu Constant. 2022. How to Dissect a Muppet: The Structure of Transformer Embedding Spaces. Transactions of the Association for Computational Linguistics, 10:981–996.