<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alfter-appelgren-2025-grasp">
    <titleInfo>
        <title>GRASP at CoMeDi Shared Task: Multi-Strategy Modeling of Annotator Behavior in Multi-Lingual Semantic Judgments</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Alfter</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mattias</namePart>
        <namePart type="family">Appelgren</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of Context and Meaning: Navigating Disagreements in NLP Annotation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Michael</namePart>
            <namePart type="family">Roth</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dominik</namePart>
            <namePart type="family">Schlechtweg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper presents the GRASP team‘s systems for the CoMeDi 2025 shared task on disagreement prediction in semantic annotation. The task comprises two subtasks: predicting median similarity scores and mean disagreement scores for word usage across multiple languages including Chinese, English, German, Norwegian, Russian, Spanish, and Swedish. For subtask 1, we implement three approaches: Prochain, a probabilistic chain model predicting sequential judgments; FARM, an ensemble of five fine-tuned XLM-RoBERTa models; and THAT, a task-specific model using XL-Lexeme with adaptive thresholds. For subtask 2, we develop three systems: LAMP, combining language-agnostic and monolingual models; BUMBLE, using optimal language combinations; and DRAMA, leveraging disagreement patterns from FARM‘s outputs. Our results show strong performance across both subtasks, ranking second overall among participating teams. The probabilistic Prochain model demonstrates surprisingly robust performance when given accurate initial judgments, while our task-specific approaches show varying effectiveness across languages.</abstract>
    <identifier type="citekey">alfter-appelgren-2025-grasp</identifier>
    <location>
        <url>https://aclanthology.org/2025.comedi-1.7/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>78</start>
            <end>89</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T GRASP at CoMeDi Shared Task: Multi-Strategy Modeling of Annotator Behavior in Multi-Lingual Semantic Judgments
%A Alfter, David
%A Appelgren, Mattias
%Y Roth, Michael
%Y Schlechtweg, Dominik
%S Proceedings of Context and Meaning: Navigating Disagreements in NLP Annotation
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F alfter-appelgren-2025-grasp
%X This paper presents the GRASP team‘s systems for the CoMeDi 2025 shared task on disagreement prediction in semantic annotation. The task comprises two subtasks: predicting median similarity scores and mean disagreement scores for word usage across multiple languages including Chinese, English, German, Norwegian, Russian, Spanish, and Swedish. For subtask 1, we implement three approaches: Prochain, a probabilistic chain model predicting sequential judgments; FARM, an ensemble of five fine-tuned XLM-RoBERTa models; and THAT, a task-specific model using XL-Lexeme with adaptive thresholds. For subtask 2, we develop three systems: LAMP, combining language-agnostic and monolingual models; BUMBLE, using optimal language combinations; and DRAMA, leveraging disagreement patterns from FARM‘s outputs. Our results show strong performance across both subtasks, ranking second overall among participating teams. The probabilistic Prochain model demonstrates surprisingly robust performance when given accurate initial judgments, while our task-specific approaches show varying effectiveness across languages.
%U https://aclanthology.org/2025.comedi-1.7/
%P 78-89

Markdown (Informal)

[GRASP at CoMeDi Shared Task: Multi-Strategy Modeling of Annotator Behavior in Multi-Lingual Semantic Judgments](https://aclanthology.org/2025.comedi-1.7/) (Alfter & Appelgren, CoMeDi 2025)

• GRASP at CoMeDi Shared Task: Multi-Strategy Modeling of Annotator Behavior in Multi-Lingual Semantic Judgments (Alfter & Appelgren, CoMeDi 2025)

ACL

• David Alfter and Mattias Appelgren. 2025. GRASP at CoMeDi Shared Task: Multi-Strategy Modeling of Annotator Behavior in Multi-Lingual Semantic Judgments. In Proceedings of Context and Meaning: Navigating Disagreements in NLP Annotation, pages 78–89, Abu Dhabi, UAE. International Committee on Computational Linguistics.