@inproceedings{joshi-etal-2025-posestitch,
title = "{P}ose{S}titch-{SLT}: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation",
author = "Joshi, Abhinav and
Sharma, Vaibhav and
Singh, Sanjeet and
Modi, Ashutosh",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.698/",
pages = "13845--13864",
ISBN = "979-8-89176-332-6",
abstract = "Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose PoseStitch-SLT, a novel pre-training scheme that is inspired by linguistic-templates-based sentence generation technique. With translation comparison on two sign language datasets, How2Sign and iSign, we show that a simple transformer-based encoder-decoder architecture outperforms the prior art when considering template-generated sentence pairs in training. We achieve BLEU-4 score improvements from 1.97 to 4.56 on How2Sign and from 0.55 to 3.43 on iSign, surpassing prior state-of-the-art methods for pose-based gloss-free translation. The results demonstrate the effectiveness of template-driven synthetic supervision in low-resource sign language settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="joshi-etal-2025-posestitch">
<titleInfo>
<title>PoseStitch-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vaibhav</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Modi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose PoseStitch-SLT, a novel pre-training scheme that is inspired by linguistic-templates-based sentence generation technique. With translation comparison on two sign language datasets, How2Sign and iSign, we show that a simple transformer-based encoder-decoder architecture outperforms the prior art when considering template-generated sentence pairs in training. We achieve BLEU-4 score improvements from 1.97 to 4.56 on How2Sign and from 0.55 to 3.43 on iSign, surpassing prior state-of-the-art methods for pose-based gloss-free translation. The results demonstrate the effectiveness of template-driven synthetic supervision in low-resource sign language settings.</abstract>
<identifier type="citekey">joshi-etal-2025-posestitch</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.698/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>13845</start>
<end>13864</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PoseStitch-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation
%A Joshi, Abhinav
%A Sharma, Vaibhav
%A Singh, Sanjeet
%A Modi, Ashutosh
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F joshi-etal-2025-posestitch
%X Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose PoseStitch-SLT, a novel pre-training scheme that is inspired by linguistic-templates-based sentence generation technique. With translation comparison on two sign language datasets, How2Sign and iSign, we show that a simple transformer-based encoder-decoder architecture outperforms the prior art when considering template-generated sentence pairs in training. We achieve BLEU-4 score improvements from 1.97 to 4.56 on How2Sign and from 0.55 to 3.43 on iSign, surpassing prior state-of-the-art methods for pose-based gloss-free translation. The results demonstrate the effectiveness of template-driven synthetic supervision in low-resource sign language settings.
%U https://aclanthology.org/2025.emnlp-main.698/
%P 13845-13864
Markdown (Informal)
[PoseStitch-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation](https://aclanthology.org/2025.emnlp-main.698/) (Joshi et al., EMNLP 2025)
ACL