@inproceedings{escolano-etal-2026-lsc,
title = "{LSC}-{CARE}: An annotated dataset for medical {C}atalan {S}ign {L}anguage",
author = "Escolano, Carlos and
Cort{\'e}s, Joan Gom{\`a} and
Barber{\`a}, Gemma and
Sant, Gerard and
Melero, Maite",
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-1.6/",
pages = "54--69",
ISBN = "979-8-89176-488-0",
abstract = "Deaf signers face persistent communication barriers in healthcare settings, where reliance on third-party interpreters can compromise privacy precisely when confidentiality matters most. We present LSC-CARE, the first annotated dataset of Catalan Sign Language (LSC) for the medical domain, comprising 2,784 signed segments (approximately 4.5 hours) produced by 11 deaf native signers across ten emergency-care topics. Each segment is paired with time-aligned ID-gloss annotations produced by a deaf native linguist and written Catalan translations produced by an LSC interpreter, following conventions consistent with the LSC SignBank. To assess the dataset{'}s utility for Sign Language Translation, we benchmark three settings: a gloss-free end-to-end video-to-text model, a cascade of sign language recognition and gloss-to-text translation, and an oracle gloss-to-text upper bound. The cascade consistently outperforms the end-to-end approach despite a high gloss error rate, and, unlike it, is statistically invariant to signer identity, while the 21-BLEU gap between cascade and oracle identifies visual sign recognition as the main bottleneck for low-resource medical SLT. We release the dataset to support accessible healthcare technologies for the Catalan Deaf community."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="escolano-etal-2026-lsc">
<titleInfo>
<title>LSC-CARE: An annotated dataset for medical Catalan Sign Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Escolano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joan</namePart>
<namePart type="given">Gomà</namePart>
<namePart type="family">Cortés</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gemma</namePart>
<namePart type="family">Barberà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerard</namePart>
<namePart type="family">Sant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</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>Deaf signers face persistent communication barriers in healthcare settings, where reliance on third-party interpreters can compromise privacy precisely when confidentiality matters most. We present LSC-CARE, the first annotated dataset of Catalan Sign Language (LSC) for the medical domain, comprising 2,784 signed segments (approximately 4.5 hours) produced by 11 deaf native signers across ten emergency-care topics. Each segment is paired with time-aligned ID-gloss annotations produced by a deaf native linguist and written Catalan translations produced by an LSC interpreter, following conventions consistent with the LSC SignBank. To assess the dataset’s utility for Sign Language Translation, we benchmark three settings: a gloss-free end-to-end video-to-text model, a cascade of sign language recognition and gloss-to-text translation, and an oracle gloss-to-text upper bound. The cascade consistently outperforms the end-to-end approach despite a high gloss error rate, and, unlike it, is statistically invariant to signer identity, while the 21-BLEU gap between cascade and oracle identifies visual sign recognition as the main bottleneck for low-resource medical SLT. We release the dataset to support accessible healthcare technologies for the Catalan Deaf community.</abstract>
<identifier type="citekey">escolano-etal-2026-lsc</identifier>
<location>
<url>https://aclanthology.org/2026.wslp-1.6/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>54</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LSC-CARE: An annotated dataset for medical Catalan Sign Language
%A Escolano, Carlos
%A Cortés, Joan Gomà
%A Barberà, Gemma
%A Sant, Gerard
%A Melero, Maite
%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 escolano-etal-2026-lsc
%X Deaf signers face persistent communication barriers in healthcare settings, where reliance on third-party interpreters can compromise privacy precisely when confidentiality matters most. We present LSC-CARE, the first annotated dataset of Catalan Sign Language (LSC) for the medical domain, comprising 2,784 signed segments (approximately 4.5 hours) produced by 11 deaf native signers across ten emergency-care topics. Each segment is paired with time-aligned ID-gloss annotations produced by a deaf native linguist and written Catalan translations produced by an LSC interpreter, following conventions consistent with the LSC SignBank. To assess the dataset’s utility for Sign Language Translation, we benchmark three settings: a gloss-free end-to-end video-to-text model, a cascade of sign language recognition and gloss-to-text translation, and an oracle gloss-to-text upper bound. The cascade consistently outperforms the end-to-end approach despite a high gloss error rate, and, unlike it, is statistically invariant to signer identity, while the 21-BLEU gap between cascade and oracle identifies visual sign recognition as the main bottleneck for low-resource medical SLT. We release the dataset to support accessible healthcare technologies for the Catalan Deaf community.
%U https://aclanthology.org/2026.wslp-1.6/
%P 54-69
Markdown (Informal)
[LSC-CARE: An annotated dataset for medical Catalan Sign Language](https://aclanthology.org/2026.wslp-1.6/) (Escolano et al., WSLP 2026)
ACL