@inproceedings{krishna-etal-2026-transalign,
title = "{T}rans{A}lign-{SLT}: Complementary Temporal and Semantic Supervision for Gloss-Free Sign Language Translation",
author = "Krishna, Pallapu Mohan and
Kumar, Uppala Sanjay and
Bhuyan, M.K. and
Neog, Debanga Raj",
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-1.21/",
pages = "213--223",
ISBN = "979-8-89176-488-0",
abstract = "Gloss-free sign language translation (SLT) aims to translate sign videos directly into spoken-language sentences without relying on costly gloss annotations. However, when supervision is available only at the sentence level, the correspondence between visual dynamics and linguistic content remains weak. We introduce $\textbf{TransAlign-SLT}$, a lightweight fully gloss-free framework that derives complementary temporal and semantic supervision from the available translations. Auxiliary TranslationCTC provides coarse temporal regularization, while Masked Entropic Optimal Transport (MOT) aligns visual temporal features with contextualized word-level representations from a frozen, corpus-adapted BERT encoder. Since the semantic branch is used only during training, the inference pipeline remains lightweight and autoregressive. TransAlign-SLT achieves $\textbf{23.54 BLEU-4 / 48.46 ROUGE-L}$ on PHOENIX14T and $\textbf{16.39 BLEU-4 / 44.68 ROUGE-L}$ on CSL-Daily, with $\textbf{45.6M}$ inference parameters and $\textbf{123 GFLOPs}$. Ablation studies show that temporal modeling, semantic alignment, and decayed TranslationCTC supervision provide complementary benefits. Overall, the results show that useful visual-language structure can be learned directly from translation supervision without glosses, pseudo-glosses, or a large pretrained language decoder at inference."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishna-etal-2026-transalign">
<titleInfo>
<title>TransAlign-SLT: Complementary Temporal and Semantic Supervision for Gloss-Free Sign Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pallapu</namePart>
<namePart type="given">Mohan</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uppala</namePart>
<namePart type="given">Sanjay</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Bhuyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanga</namePart>
<namePart type="given">Raj</namePart>
<namePart type="family">Neog</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>Gloss-free sign language translation (SLT) aims to translate sign videos directly into spoken-language sentences without relying on costly gloss annotations. However, when supervision is available only at the sentence level, the correspondence between visual dynamics and linguistic content remains weak. We introduce TransAlign-SLT, a lightweight fully gloss-free framework that derives complementary temporal and semantic supervision from the available translations. Auxiliary TranslationCTC provides coarse temporal regularization, while Masked Entropic Optimal Transport (MOT) aligns visual temporal features with contextualized word-level representations from a frozen, corpus-adapted BERT encoder. Since the semantic branch is used only during training, the inference pipeline remains lightweight and autoregressive. TransAlign-SLT achieves 23.54 BLEU-4 / 48.46 ROUGE-L on PHOENIX14T and 16.39 BLEU-4 / 44.68 ROUGE-L on CSL-Daily, with 45.6M inference parameters and 123 GFLOPs. Ablation studies show that temporal modeling, semantic alignment, and decayed TranslationCTC supervision provide complementary benefits. Overall, the results show that useful visual-language structure can be learned directly from translation supervision without glosses, pseudo-glosses, or a large pretrained language decoder at inference.</abstract>
<identifier type="citekey">krishna-etal-2026-transalign</identifier>
<location>
<url>https://aclanthology.org/2026.wslp-1.21/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>213</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TransAlign-SLT: Complementary Temporal and Semantic Supervision for Gloss-Free Sign Language Translation
%A Krishna, Pallapu Mohan
%A Kumar, Uppala Sanjay
%A Bhuyan, M. K.
%A Neog, Debanga Raj
%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 krishna-etal-2026-transalign
%X Gloss-free sign language translation (SLT) aims to translate sign videos directly into spoken-language sentences without relying on costly gloss annotations. However, when supervision is available only at the sentence level, the correspondence between visual dynamics and linguistic content remains weak. We introduce TransAlign-SLT, a lightweight fully gloss-free framework that derives complementary temporal and semantic supervision from the available translations. Auxiliary TranslationCTC provides coarse temporal regularization, while Masked Entropic Optimal Transport (MOT) aligns visual temporal features with contextualized word-level representations from a frozen, corpus-adapted BERT encoder. Since the semantic branch is used only during training, the inference pipeline remains lightweight and autoregressive. TransAlign-SLT achieves 23.54 BLEU-4 / 48.46 ROUGE-L on PHOENIX14T and 16.39 BLEU-4 / 44.68 ROUGE-L on CSL-Daily, with 45.6M inference parameters and 123 GFLOPs. Ablation studies show that temporal modeling, semantic alignment, and decayed TranslationCTC supervision provide complementary benefits. Overall, the results show that useful visual-language structure can be learned directly from translation supervision without glosses, pseudo-glosses, or a large pretrained language decoder at inference.
%U https://aclanthology.org/2026.wslp-1.21/
%P 213-223
Markdown (Informal)
[TransAlign-SLT: Complementary Temporal and Semantic Supervision for Gloss-Free Sign Language Translation](https://aclanthology.org/2026.wslp-1.21/) (Krishna et al., WSLP 2026)
ACL