<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vig-2019-multiscale">
    <titleInfo>
        <title>A Multiscale Visualization of Attention in the Transformer Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jesse</namePart>
        <namePart type="family">Vig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marta</namePart>
            <namePart type="given">R</namePart>
            <namePart type="family">Costa-jussà</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Enrique</namePart>
            <namePart type="family">Alfonseca</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model by showing how the model assigns weight to different input elements. However, the multi-layer, multi-head attention mechanism in the Transformer model can be difficult to decipher. To make the model more accessible, we introduce an open-source tool that visualizes attention at multiple scales, each of which provides a unique perspective on the attention mechanism. We demonstrate the tool on BERT and OpenAI GPT-2 and present three example use cases: detecting model bias, locating relevant attention heads, and linking neurons to model behavior.</abstract>
    <identifier type="citekey">vig-2019-multiscale</identifier>
    <identifier type="doi">10.18653/v1/P19-3007</identifier>
    <location>
        <url>https://aclanthology.org/P19-3007</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>37</start>
            <end>42</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Multiscale Visualization of Attention in the Transformer Model
%A Vig, Jesse
%Y Costa-jussà, Marta R.
%Y Alfonseca, Enrique
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F vig-2019-multiscale
%X The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model by showing how the model assigns weight to different input elements. However, the multi-layer, multi-head attention mechanism in the Transformer model can be difficult to decipher. To make the model more accessible, we introduce an open-source tool that visualizes attention at multiple scales, each of which provides a unique perspective on the attention mechanism. We demonstrate the tool on BERT and OpenAI GPT-2 and present three example use cases: detecting model bias, locating relevant attention heads, and linking neurons to model behavior.
%R 10.18653/v1/P19-3007
%U https://aclanthology.org/P19-3007
%U https://doi.org/10.18653/v1/P19-3007
%P 37-42

Markdown (Informal)

[A Multiscale Visualization of Attention in the Transformer Model](https://aclanthology.org/P19-3007) (Vig, ACL 2019)

• A Multiscale Visualization of Attention in the Transformer Model (Vig, ACL 2019)

ACL

• Jesse Vig. 2019. A Multiscale Visualization of Attention in the Transformer Model. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 37–42, Florence, Italy. Association for Computational Linguistics.