@inproceedings{hwang-etal-2025-efficient,
title = "An Efficient Gloss-Free Sign Language Translation Using Spatial Configurations and Motion Dynamics with {LLM}s",
author = "Hwang, Eui Jun and
Cho, Sukmin and
Lee, Junmyeong and
Park, Jong C.",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.197/",
doi = "10.18653/v1/2025.naacl-long.197",
pages = "3901--3920",
ISBN = "979-8-89176-189-6",
abstract = "Gloss-free Sign Language Translation (SLT) converts sign videos into spoken language sentences without relying on glosses, which are the written representations of signs. Recently, Large Language Models (LLMs) have shown remarkable translation performance in gloss-free methods by harnessing their powerful natural language generation capabilities. However, these methods often rely on domain-specific fine-tuning of visual encoders to achieve optimal results. By contrast, we emphasize the importance of capturing the spatial configurations and motion dynamics in sign language. With this in mind, we introduce Spatial and Motion-based Sign Language Translation (SpaMo), a novel LLM-based SLT framework. The core idea of SpaMo is simple yet effective: instead of domain-specific tuning, we use off-the-shelf visual encoders to extract spatial and motion features, which are then input into an LLM along with a language prompt. Additionally, we employ a visual-text alignment process as a lightweight warm-up step before applying SLT supervision. Our experiments demonstrate that SpaMo achieves state-of-the-art performance on three popular datasets{---}PHOENIX14T, CSL-Daily, and How2Sign{---}without visual fine-tuning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hwang-etal-2025-efficient">
<titleInfo>
<title>An Efficient Gloss-Free Sign Language Translation Using Spatial Configurations and Motion Dynamics with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eui</namePart>
<namePart type="given">Jun</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sukmin</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junmyeong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Gloss-free Sign Language Translation (SLT) converts sign videos into spoken language sentences without relying on glosses, which are the written representations of signs. Recently, Large Language Models (LLMs) have shown remarkable translation performance in gloss-free methods by harnessing their powerful natural language generation capabilities. However, these methods often rely on domain-specific fine-tuning of visual encoders to achieve optimal results. By contrast, we emphasize the importance of capturing the spatial configurations and motion dynamics in sign language. With this in mind, we introduce Spatial and Motion-based Sign Language Translation (SpaMo), a novel LLM-based SLT framework. The core idea of SpaMo is simple yet effective: instead of domain-specific tuning, we use off-the-shelf visual encoders to extract spatial and motion features, which are then input into an LLM along with a language prompt. Additionally, we employ a visual-text alignment process as a lightweight warm-up step before applying SLT supervision. Our experiments demonstrate that SpaMo achieves state-of-the-art performance on three popular datasets—PHOENIX14T, CSL-Daily, and How2Sign—without visual fine-tuning.</abstract>
<identifier type="citekey">hwang-etal-2025-efficient</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.197</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.197/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3901</start>
<end>3920</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Efficient Gloss-Free Sign Language Translation Using Spatial Configurations and Motion Dynamics with LLMs
%A Hwang, Eui Jun
%A Cho, Sukmin
%A Lee, Junmyeong
%A Park, Jong C.
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F hwang-etal-2025-efficient
%X Gloss-free Sign Language Translation (SLT) converts sign videos into spoken language sentences without relying on glosses, which are the written representations of signs. Recently, Large Language Models (LLMs) have shown remarkable translation performance in gloss-free methods by harnessing their powerful natural language generation capabilities. However, these methods often rely on domain-specific fine-tuning of visual encoders to achieve optimal results. By contrast, we emphasize the importance of capturing the spatial configurations and motion dynamics in sign language. With this in mind, we introduce Spatial and Motion-based Sign Language Translation (SpaMo), a novel LLM-based SLT framework. The core idea of SpaMo is simple yet effective: instead of domain-specific tuning, we use off-the-shelf visual encoders to extract spatial and motion features, which are then input into an LLM along with a language prompt. Additionally, we employ a visual-text alignment process as a lightweight warm-up step before applying SLT supervision. Our experiments demonstrate that SpaMo achieves state-of-the-art performance on three popular datasets—PHOENIX14T, CSL-Daily, and How2Sign—without visual fine-tuning.
%R 10.18653/v1/2025.naacl-long.197
%U https://aclanthology.org/2025.naacl-long.197/
%U https://doi.org/10.18653/v1/2025.naacl-long.197
%P 3901-3920
Markdown (Informal)
[An Efficient Gloss-Free Sign Language Translation Using Spatial Configurations and Motion Dynamics with LLMs](https://aclanthology.org/2025.naacl-long.197/) (Hwang et al., NAACL 2025)
ACL