Extracting Signs from Weakly Aligned Sign Language Corpora: A Study on LSF and LSM

Lorena de la Garza, Julie Halbout, Julie Lascar, Niels Martinez, Arturo Curiel, Michèle Gouiffès, Annelies Braffort


Abstract
This paper presents a framework for the automatic annotation of sign language data across different recording conditions, including original and interpreted content. The proposed approach integrates weak alignment, sign segmentation, and multiple instance learning with a contrastive loss. The resulting annotations are subsequently refined and filtered to enhance their reliability. Our method was applied to two historically related sign languages, French Sign Language (LSF) and Mexican Sign Language (LSM). This led to the creation of two signaries, comprising approximately 2k categories in LSF (25k occurrences) and 41 categories in LSM (1k occurrences). Both resources provide valuable support for future research in artificial intelligence and linguistics, particularly for comparative analyses between the two languages. A seminal analysis is presented as part of this paper.
Anthology ID:
2026.signlang-1.19
Volume:
Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Eleni Efthimiou, Stavroula-Evita Fotinea, Thomas Hanke, Julie A. Hochgesang, Johanna Mesch, Marc Schulder
Venues:
SignLang | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
174–183
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-signlang-19
DOI:
10.63317/38kfot52b4dz
Bibkey:
Cite (ACL):
Lorena de la Garza, Julie Halbout, Julie Lascar, Niels Martinez, Arturo Curiel, Michèle Gouiffès, and Annelies Braffort. 2026. Extracting Signs from Weakly Aligned Sign Language Corpora: A Study on LSF and LSM. In Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion, pages 174–183, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Extracting Signs from Weakly Aligned Sign Language Corpora: A Study on LSF and LSM (de la Garza et al., SignLang 2026)
Copy Citation: