<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2020-scheduled">
    <titleInfo>
        <title>Scheduled DropHead: A Regularization Method for Transformer Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wangchunshu</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tao</namePart>
        <namePart type="family">Ge</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Furu</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ming</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ke</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</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>We introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism which is a key component of transformer. In contrast to the conventional dropout mechanism which randomly drops units or connections, DropHead drops entire attention heads during training to prevent the multi-head attention model from being dominated by a small portion of attention heads. It can help reduce the risk of overfitting and allow the models to better benefit from the multi-head attention. Given the interaction between multi-headedness and training dynamics, we further propose a novel dropout rate scheduler to adjust the dropout rate of DropHead throughout training, which results in a better regularization effect. Experimental results demonstrate that our proposed approach can improve transformer models by 0.9 BLEU score on WMT14 En-De translation task and around 1.0 accuracy for various text classification tasks.</abstract>
    <identifier type="citekey">zhou-etal-2020-scheduled</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.178</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.178</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>1971</start>
            <end>1980</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Scheduled DropHead: A Regularization Method for Transformer Models
%A Zhou, Wangchunshu
%A Ge, Tao
%A Wei, Furu
%A Zhou, Ming
%A Xu, Ke
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F zhou-etal-2020-scheduled
%X We introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism which is a key component of transformer. In contrast to the conventional dropout mechanism which randomly drops units or connections, DropHead drops entire attention heads during training to prevent the multi-head attention model from being dominated by a small portion of attention heads. It can help reduce the risk of overfitting and allow the models to better benefit from the multi-head attention. Given the interaction between multi-headedness and training dynamics, we further propose a novel dropout rate scheduler to adjust the dropout rate of DropHead throughout training, which results in a better regularization effect. Experimental results demonstrate that our proposed approach can improve transformer models by 0.9 BLEU score on WMT14 En-De translation task and around 1.0 accuracy for various text classification tasks.
%R 10.18653/v1/2020.findings-emnlp.178
%U https://aclanthology.org/2020.findings-emnlp.178
%U https://doi.org/10.18653/v1/2020.findings-emnlp.178
%P 1971-1980

Markdown (Informal)

[Scheduled DropHead: A Regularization Method for Transformer Models](https://aclanthology.org/2020.findings-emnlp.178) (Zhou et al., Findings 2020)

• Scheduled DropHead: A Regularization Method for Transformer Models (Zhou et al., Findings 2020)

ACL

• Wangchunshu Zhou, Tao Ge, Furu Wei, Ming Zhou, and Ke Xu. 2020. Scheduled DropHead: A Regularization Method for Transformer Models. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1971–1980, Online. Association for Computational Linguistics.