<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2026-masa">
    <titleInfo>
        <title>MASA: A Novel Multimodal Foundation Model for L2 Speaking Assessment in Picture-description Scenarios</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bi-Cheng</namePart>
        <namePart type="family">Yan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fu-An</namePart>
        <namePart type="family">Chao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hong-Yun</namePart>
        <namePart type="given">H.Y.</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Berlin</namePart>
        <namePart type="family">Chen</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 Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Automatic speaking assessment (ASA) manages to quantify the language competence of second language (L2) learners by providing a proficiency score based on their spoken responses. Existing efforts typically employ a neural grader coupled with a set of handcrafted features to gauge the competence of language in L2 learners from multiple facets. Despite their decent efficacy, these methods are limited by a laborious feature engineering process and largely overlook the utilization of scoring rubrics that are presented to human raters in speaking assessment. In light of this, we put forward a novel Multimodal foundation model for ASA, termed MASA, for use in picture-description scenarios. Our approach effectively streamlines the feature engineering process by leveraging the pre-trained encoders of a multimodal foundation model, and emulates the nuanced scoring behaviors of human raters by incorporating scoring rubrics directly into the modeling process. Furthermore, a simple, training-free method is introduced to alleviate the scoring bias in MASA by contrasting the output distributions derived from the multimodal and single-modal inputs. A series of experiments conducted on a picture-description task of the General English Proficiency Test (GEPT) dataset validates the feasibility and superiority of our method in comparison to several cutting-edge baselines.</abstract>
    <identifier type="citekey">yan-etal-2026-masa</identifier>
    <identifier type="doi">10.63317/2yc5vwhcevz5</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.433/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>5545</start>
            <end>5554</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MASA: A Novel Multimodal Foundation Model for L2 Speaking Assessment in Picture-description Scenarios
%A Yan, Bi-Cheng
%A Chao, Fu-An
%A Lin, Hong-Yun H.Y.
%A Chen, Berlin
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F yan-etal-2026-masa
%X Automatic speaking assessment (ASA) manages to quantify the language competence of second language (L2) learners by providing a proficiency score based on their spoken responses. Existing efforts typically employ a neural grader coupled with a set of handcrafted features to gauge the competence of language in L2 learners from multiple facets. Despite their decent efficacy, these methods are limited by a laborious feature engineering process and largely overlook the utilization of scoring rubrics that are presented to human raters in speaking assessment. In light of this, we put forward a novel Multimodal foundation model for ASA, termed MASA, for use in picture-description scenarios. Our approach effectively streamlines the feature engineering process by leveraging the pre-trained encoders of a multimodal foundation model, and emulates the nuanced scoring behaviors of human raters by incorporating scoring rubrics directly into the modeling process. Furthermore, a simple, training-free method is introduced to alleviate the scoring bias in MASA by contrasting the output distributions derived from the multimodal and single-modal inputs. A series of experiments conducted on a picture-description task of the General English Proficiency Test (GEPT) dataset validates the feasibility and superiority of our method in comparison to several cutting-edge baselines.
%R 10.63317/2yc5vwhcevz5
%U https://aclanthology.org/2026.lrec-1.433/
%U https://doi.org/10.63317/2yc5vwhcevz5
%P 5545-5554

Markdown (Informal)

[MASA: A Novel Multimodal Foundation Model for L2 Speaking Assessment in Picture-description Scenarios](https://aclanthology.org/2026.lrec-1.433/) (Yan et al., LREC 2026)

• MASA: A Novel Multimodal Foundation Model for L2 Speaking Assessment in Picture-description Scenarios (Yan et al., LREC 2026)

ACL

• Bi-Cheng Yan, Fu-An Chao, Hong-Yun H.Y. Lin, and Berlin Chen. 2026. MASA: A Novel Multimodal Foundation Model for L2 Speaking Assessment in Picture-description Scenarios. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5545–5554, Palma de Mallorca, Spain. ELRA Language Resource Association.