<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-fima">
    <titleInfo>
        <title>FiMA: Redundancy-Aware Description Enhancement for Gloss-Free Sign Language Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Peidong</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lianyu</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Feng</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>Gloss-free Sign Language Translation (SLT) avoids costly gloss annotations but remains limited by weak visual-text alignment. Recent MLLM-based methods use frame descriptions as auxiliary supervision, yet these descriptions are often repetitive, producing nearly identical text features; meanwhile, global pooling washes out sparse but meaningful gestures. We propose FiMA (Fine-grained Multimodal Alignment), a pre-training framework for redundancy-aware description enhancement. FiMA combines a Description Enhancement Module, which removes shared template redundancy from description features, with a Multimodal Alignment Module, which aligns each text token to its most relevant visual frame through Max-Sim matching. On PHOENIX14T and CSL-Daily, FiMA achieves state-of-the-art gloss-free SLT performance and visualizations show clearer feature separation and temporal grounding. The code will be released at https://github.com/Ryeliu/FiMA.</abstract>
    <identifier type="citekey">liu-etal-2026-fima</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2253/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>51247</start>
            <end>51259</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T FiMA: Redundancy-Aware Description Enhancement for Gloss-Free Sign Language Translation
%A Liu, Peidong
%A Hu, Lianyu
%A Feng, Wei
%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 liu-etal-2026-fima
%X Gloss-free Sign Language Translation (SLT) avoids costly gloss annotations but remains limited by weak visual-text alignment. Recent MLLM-based methods use frame descriptions as auxiliary supervision, yet these descriptions are often repetitive, producing nearly identical text features; meanwhile, global pooling washes out sparse but meaningful gestures. We propose FiMA (Fine-grained Multimodal Alignment), a pre-training framework for redundancy-aware description enhancement. FiMA combines a Description Enhancement Module, which removes shared template redundancy from description features, with a Multimodal Alignment Module, which aligns each text token to its most relevant visual frame through Max-Sim matching. On PHOENIX14T and CSL-Daily, FiMA achieves state-of-the-art gloss-free SLT performance and visualizations show clearer feature separation and temporal grounding. The code will be released at https://github.com/Ryeliu/FiMA.
%U https://aclanthology.org/2026.emnlp-main.2253/
%P 51247-51259

Markdown (Informal)

[FiMA: Redundancy-Aware Description Enhancement for Gloss-Free Sign Language Translation](https://aclanthology.org/2026.emnlp-main.2253/) (Liu et al., EMNLP 2026)

• FiMA: Redundancy-Aware Description Enhancement for Gloss-Free Sign Language Translation (Liu et al., EMNLP 2026)

ACL

• Peidong Liu, Lianyu Hu, and Wei Feng. 2026. FiMA: Redundancy-Aware Description Enhancement for Gloss-Free Sign Language Translation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 51247–51259, Budapest, Hungary. Association for Computational Linguistics.