<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maekawa-etal-2026-subjective">
    <titleInfo>
        <title>Subjective and Hierarchical Annotation of Text Difficulty in Japanese</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daisuke</namePart>
        <namePart type="family">Maekawa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kazumasa</namePart>
        <namePart type="family">Omura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sora</namePart>
        <namePart type="family">Tarumoto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shotaro</namePart>
        <namePart type="family">Ishihara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tomoyuki</namePart>
        <namePart type="family">Kajiwara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>This study presents a difficulty-annotated corpus of Japanese newspaper articles. The annotation in our corpus has two key features. First, it is hierarchical, with difficulty levels labeled at the word, sentence, and document levels, respectively. Second, it is subjective, with 99 readers from diverse backgrounds labeling the difficulty levels based on their own perceptions. Detailed analysis of our corpus revealed correlations in difficulty levels across linguistic units, such as between words and sentences, and sentences and documents. We also found that text difficulty varies depending on reader attributes such as age and topics of interest. Furthermore, we trained Transformer encoders on this corpus and developed a personalized difficulty estimation model that takes into account both linguistic and attribute information. Experimental results demonstrate that incorporating reader attributes improves the performance of difficulty estimation and that multi-task learning across language units is beneficial. Our difficulty annotations are publicly available.</abstract>
    <identifier type="citekey">maekawa-etal-2026-subjective</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.926/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>21316</start>
            <end>21327</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Subjective and Hierarchical Annotation of Text Difficulty in Japanese
%A Maekawa, Daisuke
%A Omura, Kazumasa
%A Tarumoto, Sora
%A Ishihara, Shotaro
%A Kajiwara, Tomoyuki
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F maekawa-etal-2026-subjective
%X This study presents a difficulty-annotated corpus of Japanese newspaper articles. The annotation in our corpus has two key features. First, it is hierarchical, with difficulty levels labeled at the word, sentence, and document levels, respectively. Second, it is subjective, with 99 readers from diverse backgrounds labeling the difficulty levels based on their own perceptions. Detailed analysis of our corpus revealed correlations in difficulty levels across linguistic units, such as between words and sentences, and sentences and documents. We also found that text difficulty varies depending on reader attributes such as age and topics of interest. Furthermore, we trained Transformer encoders on this corpus and developed a personalized difficulty estimation model that takes into account both linguistic and attribute information. Experimental results demonstrate that incorporating reader attributes improves the performance of difficulty estimation and that multi-task learning across language units is beneficial. Our difficulty annotations are publicly available.
%U https://aclanthology.org/2026.emnlp-main.926/
%P 21316-21327

Markdown (Informal)

[Subjective and Hierarchical Annotation of Text Difficulty in Japanese](https://aclanthology.org/2026.emnlp-main.926/) (Maekawa et al., EMNLP 2026)

• Subjective and Hierarchical Annotation of Text Difficulty in Japanese (Maekawa et al., EMNLP 2026)

ACL

• Daisuke Maekawa, Kazumasa Omura, Sora Tarumoto, Shotaro Ishihara, and Tomoyuki Kajiwara. 2026. Subjective and Hierarchical Annotation of Text Difficulty in Japanese. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 21316–21327, Budapest, Hungary. Association for Computational Linguistics.