@inproceedings{ozel-etal-2026-cross,
title = "Cross-Lingual Transfer of Self-Supervised Representations for Sign Language Translation: A Case Study for {T}urkish {S}ign {L}anguage",
author = {{\"O}zel, {\"O}zge Can and
{\c{S}}ahin, Saliha Nur and
Saraclar, Murat},
editor = "Singh, Sanjeet and
Joshi, Abhinav and
Dattatreya, Pokala and
Artiaga, Keren and
Pujara, Khushi Jaydeep and
{\v{Z}}elezn{\'y}, Tom{\'a}{\v{s}} and
Gruber, Ivan and
Honz{\'i}k, Jakub and
Kamila, Sabyasachi and
Quiroga, Facundo Manuel and
Hr{\'u}z, Marek and
Hasanuzzaman, Mohammed and
Modi, Ashutosh",
booktitle = "Proceedings of the Second Workshop on Sign Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wslp-1.16/",
pages = "162--171",
ISBN = "979-8-89176-488-0",
abstract = "Sign Language Translation (SLT) is especially difficult for low-resource languages such as Turkish Sign Language (TID), where aligned sign-text data are scarce. Self-supervised encoders pretrained on large sign corpora can reduce this dependence, but existing models are developed and evaluated almost exclusively on high-resource sign languages. One such model is SHuBERT (Sign Hidden-Unit BERT), a publicly released self-supervised contextual representation model trained on American Sign Language (ASL). We ask whether SHuBERT can be adapted to TID translation on the open-domain BUTID benchmark. Pretrained SHuBERT is incorporated into an encoder-decoder based translation model and evaluated under both frozen and fine-tuned settings. This is compared against two references trained under the same recipe: a pose baseline, and a raw-feature setting using DINOv2-encoded hand/face crops and pose. All variants outperform the pose baseline, frozen SHuBERT performs on par with raw-feature setting, and fine-tuning yields the strongest result, reaching 7.15 BLEU-4 on the test set (+1.62 over the pose baseline, +0.77 over the raw-feature setting). Our results suggest that reusing a high resource, ASL-pretrained self-supervised encoder can benefit low-resource SLT, but this benefit emerges through fine-tuning rather than frozen transfer alone."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ozel-etal-2026-cross">
<titleInfo>
<title>Cross-Lingual Transfer of Self-Supervised Representations for Sign Language Translation: A Case Study for Turkish Sign Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Özge</namePart>
<namePart type="given">Can</namePart>
<namePart type="family">Özel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="given">Nur</namePart>
<namePart type="family">Şahin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Murat</namePart>
<namePart type="family">Saraclar</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 Second Workshop on Sign Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanjeet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pokala</namePart>
<namePart type="family">Dattatreya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keren</namePart>
<namePart type="family">Artiaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khushi</namePart>
<namePart type="given">Jaydeep</namePart>
<namePart type="family">Pujara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Železný</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Gruber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Honzík</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabyasachi</namePart>
<namePart type="family">Kamila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Facundo</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="family">Quiroga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Hrúz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Hasanuzzaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Modi</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">979-8-89176-488-0</identifier>
</relatedItem>
<abstract>Sign Language Translation (SLT) is especially difficult for low-resource languages such as Turkish Sign Language (TID), where aligned sign-text data are scarce. Self-supervised encoders pretrained on large sign corpora can reduce this dependence, but existing models are developed and evaluated almost exclusively on high-resource sign languages. One such model is SHuBERT (Sign Hidden-Unit BERT), a publicly released self-supervised contextual representation model trained on American Sign Language (ASL). We ask whether SHuBERT can be adapted to TID translation on the open-domain BUTID benchmark. Pretrained SHuBERT is incorporated into an encoder-decoder based translation model and evaluated under both frozen and fine-tuned settings. This is compared against two references trained under the same recipe: a pose baseline, and a raw-feature setting using DINOv2-encoded hand/face crops and pose. All variants outperform the pose baseline, frozen SHuBERT performs on par with raw-feature setting, and fine-tuning yields the strongest result, reaching 7.15 BLEU-4 on the test set (+1.62 over the pose baseline, +0.77 over the raw-feature setting). Our results suggest that reusing a high resource, ASL-pretrained self-supervised encoder can benefit low-resource SLT, but this benefit emerges through fine-tuning rather than frozen transfer alone.</abstract>
<identifier type="citekey">ozel-etal-2026-cross</identifier>
<location>
<url>https://aclanthology.org/2026.wslp-1.16/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>162</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Transfer of Self-Supervised Representations for Sign Language Translation: A Case Study for Turkish Sign Language
%A Özel, Özge Can
%A Şahin, Saliha Nur
%A Saraclar, Murat
%Y Singh, Sanjeet
%Y Joshi, Abhinav
%Y Dattatreya, Pokala
%Y Artiaga, Keren
%Y Pujara, Khushi Jaydeep
%Y Železný, Tomáš
%Y Gruber, Ivan
%Y Honzík, Jakub
%Y Kamila, Sabyasachi
%Y Quiroga, Facundo Manuel
%Y Hrúz, Marek
%Y Hasanuzzaman, Mohammed
%Y Modi, Ashutosh
%S Proceedings of the Second Workshop on Sign Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-488-0
%F ozel-etal-2026-cross
%X Sign Language Translation (SLT) is especially difficult for low-resource languages such as Turkish Sign Language (TID), where aligned sign-text data are scarce. Self-supervised encoders pretrained on large sign corpora can reduce this dependence, but existing models are developed and evaluated almost exclusively on high-resource sign languages. One such model is SHuBERT (Sign Hidden-Unit BERT), a publicly released self-supervised contextual representation model trained on American Sign Language (ASL). We ask whether SHuBERT can be adapted to TID translation on the open-domain BUTID benchmark. Pretrained SHuBERT is incorporated into an encoder-decoder based translation model and evaluated under both frozen and fine-tuned settings. This is compared against two references trained under the same recipe: a pose baseline, and a raw-feature setting using DINOv2-encoded hand/face crops and pose. All variants outperform the pose baseline, frozen SHuBERT performs on par with raw-feature setting, and fine-tuning yields the strongest result, reaching 7.15 BLEU-4 on the test set (+1.62 over the pose baseline, +0.77 over the raw-feature setting). Our results suggest that reusing a high resource, ASL-pretrained self-supervised encoder can benefit low-resource SLT, but this benefit emerges through fine-tuning rather than frozen transfer alone.
%U https://aclanthology.org/2026.wslp-1.16/
%P 162-171
Markdown (Informal)
[Cross-Lingual Transfer of Self-Supervised Representations for Sign Language Translation: A Case Study for Turkish Sign Language](https://aclanthology.org/2026.wslp-1.16/) (Özel et al., WSLP 2026)
ACL