<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xin-etal-2020-deebert">
    <titleInfo>
        <title>DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ji</namePart>
        <namePart type="family">Xin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raphael</namePart>
        <namePart type="family">Tang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaejun</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yaoliang</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jimmy</namePart>
        <namePart type="family">Lin</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>Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We propose a simple but effective method, DeeBERT, to accelerate BERT inference. Our approach allows samples to exit earlier without passing through the entire model. Experiments show that DeeBERT is able to save up to ~40% inference time with minimal degradation in model quality. Further analyses show different behaviors in the BERT transformer layers and also reveal their redundancy. Our work provides new ideas to efficiently apply deep transformer-based models to downstream tasks. Code is available at https://github.com/castorini/DeeBERT.</abstract>
    <identifier type="citekey">xin-etal-2020-deebert</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.204</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.204</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>2246</start>
            <end>2251</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
%A Xin, Ji
%A Tang, Raphael
%A Lee, Jaejun
%A Yu, Yaoliang
%A Lin, Jimmy
%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 xin-etal-2020-deebert
%X Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We propose a simple but effective method, DeeBERT, to accelerate BERT inference. Our approach allows samples to exit earlier without passing through the entire model. Experiments show that DeeBERT is able to save up to ~40% inference time with minimal degradation in model quality. Further analyses show different behaviors in the BERT transformer layers and also reveal their redundancy. Our work provides new ideas to efficiently apply deep transformer-based models to downstream tasks. Code is available at https://github.com/castorini/DeeBERT.
%R 10.18653/v1/2020.acl-main.204
%U https://aclanthology.org/2020.acl-main.204
%U https://doi.org/10.18653/v1/2020.acl-main.204
%P 2246-2251

Markdown (Informal)

[DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference](https://aclanthology.org/2020.acl-main.204) (Xin et al., ACL 2020)

• DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference (Xin et al., ACL 2020)

ACL

• Ji Xin, Raphael Tang, Jaejun Lee, Yaoliang Yu, and Jimmy Lin. 2020. DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2246–2251, Online. Association for Computational Linguistics.