<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shelmanov-etal-2021-certain">
    <titleInfo>
        <title>How Certain is Your Transformer?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Artem</namePart>
        <namePart type="family">Shelmanov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Evgenii</namePart>
        <namePart type="family">Tsymbalov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dmitri</namePart>
        <namePart type="family">Puzyrev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kirill</namePart>
        <namePart type="family">Fedyanin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Panchenko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maxim</namePart>
        <namePart type="family">Panov</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 consider the problem of uncertainty estimation for Transformer-based models. We investigate the applicability of uncertainty estimates based on dropout usage at the inference stage (Monte Carlo dropout). The series of experiments on natural language understanding tasks shows that the resulting uncertainty estimates improve the quality of detection of error-prone instances. Special attention is paid to the construction of computationally inexpensive estimates via Monte Carlo dropout and Determinantal Point Processes.</abstract>
    <identifier type="citekey">shelmanov-etal-2021-certain</identifier>
    <identifier type="doi">10.18653/v1/2021.eacl-main.157</identifier>
    <location>
        <url>https://aclanthology.org/2021.eacl-main.157</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>1833</start>
            <end>1840</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T How Certain is Your Transformer?
%A Shelmanov, Artem
%A Tsymbalov, Evgenii
%A Puzyrev, Dmitri
%A Fedyanin, Kirill
%A Panchenko, Alexander
%A Panov, Maxim
%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 shelmanov-etal-2021-certain
%X In this work, we consider the problem of uncertainty estimation for Transformer-based models. We investigate the applicability of uncertainty estimates based on dropout usage at the inference stage (Monte Carlo dropout). The series of experiments on natural language understanding tasks shows that the resulting uncertainty estimates improve the quality of detection of error-prone instances. Special attention is paid to the construction of computationally inexpensive estimates via Monte Carlo dropout and Determinantal Point Processes.
%R 10.18653/v1/2021.eacl-main.157
%U https://aclanthology.org/2021.eacl-main.157
%U https://doi.org/10.18653/v1/2021.eacl-main.157
%P 1833-1840

Markdown (Informal)

[How Certain is Your Transformer?](https://aclanthology.org/2021.eacl-main.157) (Shelmanov et al., EACL 2021)

• How Certain is Your Transformer? (Shelmanov et al., EACL 2021)

ACL

• Artem Shelmanov, Evgenii Tsymbalov, Dmitri Puzyrev, Kirill Fedyanin, Alexander Panchenko, and Maxim Panov. 2021. How Certain is Your Transformer?. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1833–1840, Online. Association for Computational Linguistics.