<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sazonov-etal-2026-lost">
    <titleInfo>
        <title>Lost in Expression: Diagnosing Systemic Challenges with Non-Manual Generalization in Sign Language Understanding Tasks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dmitriy</namePart>
        <namePart type="family">Sazonov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sevgi</namePart>
        <namePart type="given">Z</namePart>
        <namePart type="family">Gurbuz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Evie</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Malaia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Eleni</namePart>
            <namePart type="family">Efthimiou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stavroula-Evita</namePart>
            <namePart type="family">Fotinea</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thomas</namePart>
            <namePart type="family">Hanke</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julie</namePart>
            <namePart type="given">A</namePart>
            <namePart type="family">Hochgesang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Johanna</namePart>
            <namePart type="family">Mesch</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marc</namePart>
            <namePart type="family">Schulder</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Incorporation of non-manual information is one of the most challenging aspects of Sign Language Understanding (SLU), as these features contribute to the semantic, syntactic, and pragmatic structure of signed communication as a critical feature of compositional meaning at sign, phrase and sentence level. Despite their key linguistic role, non-manuals are often an afterthought in SLU model and dataset design, with many recent models still neglecting to implement non-manual analysis or evaluate how articulators beyond the hands are contributing to the model prediction. In this work, we identify and analyze the challenges relating to recognition of non-manuals and generalization of their linguistic roles encountered by SLU models, offering new explanations for failures to properly model non-manual behavior. We perform a case study on the subtasks of Continuous Sign Language Recognition and Sign Language Translation by applying the Uni-Sign model to Isharah-1000, a Saudi Sign Language dataset. Using controlled partitioning and feature attribution, we further analyze model behavior and failure cases. With this work we hope to set the stage for the creation of diagnostic frameworks for generalization of non-manuals.</abstract>
    <identifier type="citekey">sazonov-etal-2026-lost</identifier>
    <identifier type="doi">10.63317/3ofdq6bwkwik</identifier>
    <location>
        <url>https://aclanthology.org/2026.signlang-1.45/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>438</start>
            <end>449</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Lost in Expression: Diagnosing Systemic Challenges with Non-Manual Generalization in Sign Language Understanding Tasks
%A Sazonov, Dmitriy
%A Gurbuz, Sevgi Z.
%A Malaia, Evie A.
%Y Efthimiou, Eleni
%Y Fotinea, Stavroula-Evita
%Y Hanke, Thomas
%Y Hochgesang, Julie A.
%Y Mesch, Johanna
%Y Schulder, Marc
%S Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F sazonov-etal-2026-lost
%X Incorporation of non-manual information is one of the most challenging aspects of Sign Language Understanding (SLU), as these features contribute to the semantic, syntactic, and pragmatic structure of signed communication as a critical feature of compositional meaning at sign, phrase and sentence level. Despite their key linguistic role, non-manuals are often an afterthought in SLU model and dataset design, with many recent models still neglecting to implement non-manual analysis or evaluate how articulators beyond the hands are contributing to the model prediction. In this work, we identify and analyze the challenges relating to recognition of non-manuals and generalization of their linguistic roles encountered by SLU models, offering new explanations for failures to properly model non-manual behavior. We perform a case study on the subtasks of Continuous Sign Language Recognition and Sign Language Translation by applying the Uni-Sign model to Isharah-1000, a Saudi Sign Language dataset. Using controlled partitioning and feature attribution, we further analyze model behavior and failure cases. With this work we hope to set the stage for the creation of diagnostic frameworks for generalization of non-manuals.
%R 10.63317/3ofdq6bwkwik
%U https://aclanthology.org/2026.signlang-1.45/
%U https://doi.org/10.63317/3ofdq6bwkwik
%P 438-449

Markdown (Informal)

[Lost in Expression: Diagnosing Systemic Challenges with Non-Manual Generalization in Sign Language Understanding Tasks](https://aclanthology.org/2026.signlang-1.45/) (Sazonov et al., SignLang 2026)

• Lost in Expression: Diagnosing Systemic Challenges with Non-Manual Generalization in Sign Language Understanding Tasks (Sazonov et al., SignLang 2026)

ACL

• Dmitriy Sazonov, Sevgi Z. Gurbuz, and Evie A. Malaia. 2026. Lost in Expression: Diagnosing Systemic Challenges with Non-Manual Generalization in Sign Language Understanding Tasks. In Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion, pages 438–449, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).