<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-de-marneffe-2021-thinks">
    <titleInfo>
        <title>He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nanjiang</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marie-Catherine</namePart>
        <namePart type="family">de Marneffe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>We investigate how well BERT performs on predicting factuality in several existing English datasets, encompassing various linguistic constructions. Although BERT obtains a strong performance on most datasets, it does so by exploiting common surface patterns that correlate with certain factuality labels, and it fails on instances where pragmatic reasoning is necessary. Contrary to what the high performance suggests, we are still far from having a robust system for factuality prediction.</abstract>
    <identifier type="citekey">jiang-de-marneffe-2021-thinks</identifier>
    <identifier type="doi">10.1162/tacl_a_00414</identifier>
    <location>
        <url>https://aclanthology.org/2021.tacl-1.64</url>
    </location>
    <part>
        <date>2021</date>
        <detail type="volume"><number>9</number></detail>
        <extent unit="page">
            <start>1081</start>
            <end>1097</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics
%A Jiang, Nanjiang
%A de Marneffe, Marie-Catherine
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F jiang-de-marneffe-2021-thinks
%X We investigate how well BERT performs on predicting factuality in several existing English datasets, encompassing various linguistic constructions. Although BERT obtains a strong performance on most datasets, it does so by exploiting common surface patterns that correlate with certain factuality labels, and it fails on instances where pragmatic reasoning is necessary. Contrary to what the high performance suggests, we are still far from having a robust system for factuality prediction.
%R 10.1162/tacl_a_00414
%U https://aclanthology.org/2021.tacl-1.64
%U https://doi.org/10.1162/tacl_a_00414
%P 1081-1097

Markdown (Informal)

[He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics](https://aclanthology.org/2021.tacl-1.64) (Jiang & de Marneffe, TACL 2021)

• He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics (Jiang & de Marneffe, TACL 2021)

ACL

• Nanjiang Jiang and Marie-Catherine de Marneffe. 2021. He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics. Transactions of the Association for Computational Linguistics, 9:1081–1097.