<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="you-etal-2020-hard">
    <titleInfo>
        <title>Hard-Coded Gaussian Attention for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weiqiu</namePart>
        <namePart type="family">You</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Simeng</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohit</namePart>
        <namePart type="family">Iyyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dan</namePart>
            <namePart type="family">Jurafsky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Chai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Natalie</namePart>
            <namePart type="family">Schluter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joel</namePart>
            <namePart type="family">Tetreault</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent work has questioned the importance of the Transformer’s multi-headed attention for achieving high translation quality. We push further in this direction by developing a “hard-coded” attention variant without any learned parameters. Surprisingly, replacing all learned self-attention heads in the encoder and decoder with fixed, input-agnostic Gaussian distributions minimally impacts BLEU scores across four different language pairs. However, additionally, hard-coding cross attention (which connects the decoder to the encoder) significantly lowers BLEU, suggesting that it is more important than self-attention. Much of this BLEU drop can be recovered by adding just a single learned cross attention head to an otherwise hard-coded Transformer. Taken as a whole, our results offer insight into which components of the Transformer are actually important, which we hope will guide future work into the development of simpler and more efficient attention-based models.</abstract>
    <identifier type="citekey">you-etal-2020-hard</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.687</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.687</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>7689</start>
            <end>7700</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Hard-Coded Gaussian Attention for Neural Machine Translation
%A You, Weiqiu
%A Sun, Simeng
%A Iyyer, Mohit
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F you-etal-2020-hard
%X Recent work has questioned the importance of the Transformer’s multi-headed attention for achieving high translation quality. We push further in this direction by developing a “hard-coded” attention variant without any learned parameters. Surprisingly, replacing all learned self-attention heads in the encoder and decoder with fixed, input-agnostic Gaussian distributions minimally impacts BLEU scores across four different language pairs. However, additionally, hard-coding cross attention (which connects the decoder to the encoder) significantly lowers BLEU, suggesting that it is more important than self-attention. Much of this BLEU drop can be recovered by adding just a single learned cross attention head to an otherwise hard-coded Transformer. Taken as a whole, our results offer insight into which components of the Transformer are actually important, which we hope will guide future work into the development of simpler and more efficient attention-based models.
%R 10.18653/v1/2020.acl-main.687
%U https://aclanthology.org/2020.acl-main.687
%U https://doi.org/10.18653/v1/2020.acl-main.687
%P 7689-7700

Markdown (Informal)

[Hard-Coded Gaussian Attention for Neural Machine Translation](https://aclanthology.org/2020.acl-main.687) (You et al., ACL 2020)

• Hard-Coded Gaussian Attention for Neural Machine Translation (You et al., ACL 2020)

ACL

• Weiqiu You, Simeng Sun, and Mohit Iyyer. 2020. Hard-Coded Gaussian Attention for Neural Machine Translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7689–7700, Online. Association for Computational Linguistics.