<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xin-etal-2021-berxit">
    <titleInfo>
        <title>BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression</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">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>2021-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Paola</namePart>
            <namePart type="family">Merlo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jorg</namePart>
            <namePart type="family">Tiedemann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Reut</namePart>
            <namePart type="family">Tsarfaty</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>The slow speed of BERT has motivated much research on accelerating its inference, and the early exiting idea has been proposed to make trade-offs between model quality and efficiency. This paper aims to address two weaknesses of previous work: (1) existing fine-tuning strategies for early exiting models fail to take full advantage of BERT; (2) methods to make exiting decisions are limited to classification tasks. We propose a more advanced fine-tuning strategy and a learning-to-exit module that extends early exiting to tasks other than classification. Experiments demonstrate improved early exiting for BERT, with better trade-offs obtained by the proposed fine-tuning strategy, successful application to regression tasks, and the possibility to combine it with other acceleration methods. Source code can be found at https://github.com/castorini/berxit.</abstract>
    <identifier type="citekey">xin-etal-2021-berxit</identifier>
    <identifier type="doi">10.18653/v1/2021.eacl-main.8</identifier>
    <location>
        <url>https://aclanthology.org/2021.eacl-main.8/</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>91</start>
            <end>104</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression
%A Xin, Ji
%A Tang, Raphael
%A Yu, Yaoliang
%A Lin, Jimmy
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F xin-etal-2021-berxit
%X The slow speed of BERT has motivated much research on accelerating its inference, and the early exiting idea has been proposed to make trade-offs between model quality and efficiency. This paper aims to address two weaknesses of previous work: (1) existing fine-tuning strategies for early exiting models fail to take full advantage of BERT; (2) methods to make exiting decisions are limited to classification tasks. We propose a more advanced fine-tuning strategy and a learning-to-exit module that extends early exiting to tasks other than classification. Experiments demonstrate improved early exiting for BERT, with better trade-offs obtained by the proposed fine-tuning strategy, successful application to regression tasks, and the possibility to combine it with other acceleration methods. Source code can be found at https://github.com/castorini/berxit.
%R 10.18653/v1/2021.eacl-main.8
%U https://aclanthology.org/2021.eacl-main.8/
%U https://doi.org/10.18653/v1/2021.eacl-main.8
%P 91-104

Markdown (Informal)

[BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression](https://aclanthology.org/2021.eacl-main.8/) (Xin et al., EACL 2021)

• BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression (Xin et al., EACL 2021)

ACL

• Ji Xin, Raphael Tang, Yaoliang Yu, and Jimmy Lin. 2021. BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 91–104, Online. Association for Computational Linguistics.