<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-investigating">
    <titleInfo>
        <title>Investigating associative, switchable and negatable Winograd items on renewed French data sets</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiaoou</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Olga</namePart>
        <namePart type="family">Seminck</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pascal</namePart>
        <namePart type="family">Amsili</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Actes de la 29e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale</title>
        </titleInfo>
        <originInfo>
            <publisher>ATALA</publisher>
            <place>
                <placeTerm type="text">Avignon, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The Winograd Schema Challenge (WSC) consists of a set of anaphora resolution problems resolvable only by reasoning about world knowledge. This article describes the update of the existing French data set and the creation of three subsets allowing for a more robust, fine-grained evaluation protocol of WSC in French (FWSC) : an associative subset (items easily resolvable with lexical co-occurrence), a switchable subset (items where the inversion of two keywords reverses the answer) and a negatable subset (items where applying negation on its verb reverses the answer). Experiences on these data sets with CamemBERT reach SOTA performances. Our evaluation protocol showed in addition that the higher performance could be explained by the existence of associative items in FWSC. Besides, increasing the size of training corpus improves the model’s performance on switchable items while the impact of larger training corpus remains small on negatable items.</abstract>
    <identifier type="citekey">wang-etal-2022-investigating</identifier>
    <location>
        <url>https://aclanthology.org/2022.jeptalnrecital-taln.13</url>
    </location>
    <part>
        <date>2022-6</date>
        <extent unit="page">
            <start>136</start>
            <end>143</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Investigating associative, switchable and negatable Winograd items on renewed French data sets
%A Wang, Xiaoou
%A Seminck, Olga
%A Amsili, Pascal
%S Actes de la 29e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale
%D 2022
%8 June
%I ATALA
%C Avignon, France
%F wang-etal-2022-investigating
%X The Winograd Schema Challenge (WSC) consists of a set of anaphora resolution problems resolvable only by reasoning about world knowledge. This article describes the update of the existing French data set and the creation of three subsets allowing for a more robust, fine-grained evaluation protocol of WSC in French (FWSC) : an associative subset (items easily resolvable with lexical co-occurrence), a switchable subset (items where the inversion of two keywords reverses the answer) and a negatable subset (items where applying negation on its verb reverses the answer). Experiences on these data sets with CamemBERT reach SOTA performances. Our evaluation protocol showed in addition that the higher performance could be explained by the existence of associative items in FWSC. Besides, increasing the size of training corpus improves the model’s performance on switchable items while the impact of larger training corpus remains small on negatable items.
%U https://aclanthology.org/2022.jeptalnrecital-taln.13
%P 136-143

Markdown (Informal)

[Investigating associative, switchable and negatable Winograd items on renewed French data sets](https://aclanthology.org/2022.jeptalnrecital-taln.13) (Wang et al., JEP/TALN/RECITAL 2022)

• Investigating associative, switchable and negatable Winograd items on renewed French data sets (Wang et al., JEP/TALN/RECITAL 2022)

ACL

• Xiaoou Wang, Olga Seminck, and Pascal Amsili. 2022. Investigating associative, switchable and negatable Winograd items on renewed French data sets. In Actes de la 29e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale, pages 136–143, Avignon, France. ATALA.