<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roussel-2024-adapting">
    <titleInfo>
        <title>Adapting Measures of Literality for Use with Historical Language Data</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Roussel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mika</namePart>
            <namePart type="family">Hämäläinen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Emily</namePart>
            <namePart type="family">Öhman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">So</namePart>
            <namePart type="family">Miyagawa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Khalid</namePart>
            <namePart type="family">Alnajjar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yuri</namePart>
            <namePart type="family">Bizzoni</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper concerns the adaptation of two existing computational measures relating to the estimation of the literality of expressions to enable their use in scenarios where data is scarce, as is usually the case with historical language data. Being able to determine an expression’s literality via statistical means could support a range of linguistic annotation tasks, such as those relating to metaphor, metonymy, and idiomatic expressions, however making this judgment is especially difficult for modern annotators of historical and ancient texts. Therefore we re-implement these measures using smaller corpora and count-based vectors more suited to these amounts of training data. The adapted measures are evaluated against an existing data set of particle verbs annotated with degrees of literality. The results were inconclusive, yielding low correlations between 0.05 and 0.10 (Spearman’s ρ). Further work is needed to determine which measures and types of data correspond to which aspects of literality.</abstract>
    <identifier type="citekey">roussel-2024-adapting</identifier>
    <location>
        <url>https://aclanthology.org/2024.nlp4dh-1.20</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>209</start>
            <end>215</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Adapting Measures of Literality for Use with Historical Language Data
%A Roussel, Adam
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Miyagawa, So
%Y Alnajjar, Khalid
%Y Bizzoni, Yuri
%S Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, USA
%F roussel-2024-adapting
%X This paper concerns the adaptation of two existing computational measures relating to the estimation of the literality of expressions to enable their use in scenarios where data is scarce, as is usually the case with historical language data. Being able to determine an expression’s literality via statistical means could support a range of linguistic annotation tasks, such as those relating to metaphor, metonymy, and idiomatic expressions, however making this judgment is especially difficult for modern annotators of historical and ancient texts. Therefore we re-implement these measures using smaller corpora and count-based vectors more suited to these amounts of training data. The adapted measures are evaluated against an existing data set of particle verbs annotated with degrees of literality. The results were inconclusive, yielding low correlations between 0.05 and 0.10 (Spearman’s ρ). Further work is needed to determine which measures and types of data correspond to which aspects of literality.
%U https://aclanthology.org/2024.nlp4dh-1.20
%P 209-215

Markdown (Informal)

[Adapting Measures of Literality for Use with Historical Language Data](https://aclanthology.org/2024.nlp4dh-1.20) (Roussel, NLP4DH 2024)

• Adapting Measures of Literality for Use with Historical Language Data (Roussel, NLP4DH 2024)

ACL

• Adam Roussel. 2024. Adapting Measures of Literality for Use with Historical Language Data. In Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities, pages 209–215, Miami, USA. Association for Computational Linguistics.