<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2021-joint">
    <titleInfo>
        <title>Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tianxing</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bryan</namePart>
        <namePart type="family">McCann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Caiming</namePart>
        <namePart type="family">Xiong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ehsan</namePart>
        <namePart type="family">Hosseini-Asl</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>In this work, we explore joint energy-based model (EBM) training during the finetuning of pretrained text encoders (e.g., Roberta) for natural language understanding (NLU) tasks. Our experiments show that EBM training can help the model reach a better calibration that is competitive to strong baselines, with little or no loss in accuracy. We discuss three variants of energy functions (namely scalar, hidden, and sharp-hidden) that can be defined on top of a text encoder, and compare them in experiments. Due to the discreteness of text data, we adopt noise contrastive estimation (NCE) to train the energy-based model. To make NCE training more effective, we train an auto-regressive noise model with the masked language model (MLM) objective.</abstract>
    <identifier type="citekey">he-etal-2021-joint</identifier>
    <identifier type="doi">10.18653/v1/2021.eacl-main.151</identifier>
    <location>
        <url>https://aclanthology.org/2021.eacl-main.151</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>1754</start>
            <end>1761</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models
%A He, Tianxing
%A McCann, Bryan
%A Xiong, Caiming
%A Hosseini-Asl, Ehsan
%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 he-etal-2021-joint
%X In this work, we explore joint energy-based model (EBM) training during the finetuning of pretrained text encoders (e.g., Roberta) for natural language understanding (NLU) tasks. Our experiments show that EBM training can help the model reach a better calibration that is competitive to strong baselines, with little or no loss in accuracy. We discuss three variants of energy functions (namely scalar, hidden, and sharp-hidden) that can be defined on top of a text encoder, and compare them in experiments. Due to the discreteness of text data, we adopt noise contrastive estimation (NCE) to train the energy-based model. To make NCE training more effective, we train an auto-regressive noise model with the masked language model (MLM) objective.
%R 10.18653/v1/2021.eacl-main.151
%U https://aclanthology.org/2021.eacl-main.151
%U https://doi.org/10.18653/v1/2021.eacl-main.151
%P 1754-1761

Markdown (Informal)

[Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models](https://aclanthology.org/2021.eacl-main.151) (He et al., EACL 2021)

• Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models (He et al., EACL 2021)

ACL

• Tianxing He, Bryan McCann, Caiming Xiong, and Ehsan Hosseini-Asl. 2021. Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1754–1761, Online. Association for Computational Linguistics.