Segmentation of Signs for Research Purposes: Comparing Humans and Machines

Bencie Woll, Neil Fox, Kearsy Cormier

Abstract
Sign languages such as British Sign Language (BSL) are visual languages which lack standard writing systems. Annotation of sign language data, especially for the purposes of machine readability, is therefore extremely slow. Tools to help automate and thus speed up the annotation process are very much needed. Here we test the development of one such tool (VIA-SLA), which uses temporal convolutional networks (Renz et al., 2021a, b) for the purpose of segmenting continuous signing in any sign language, and is designed to integrate smoothly with ELAN, the widely used annotation software for analysis of videos of sign language. We compare automatic segmentation by machine with segmentation done by a human, both in terms of time needed and accuracy of segmentation, using samples taken from the BSL Corpus (Schembri et al., 2014). A small sample of four short video files is tested (mean duration 25 seconds). We find that mean accuracy in terms of number and location of segmentations is relatively high, at around 78%. This preliminary test suggests that VIA-SLA promises to be very useful for sign linguists.
Anthology ID:
2022.signlang-1.31
Volume:
Proceedings of the LREC2022 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources
Month:
June
Year:
2022
Address:
Marseille, France
Venue:
SignLang
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
198–201
Language:
URL:
https://aclanthology.org/2022.signlang-1.31
DOI:
Bibkey:
Cite (ACL):
Bencie Woll, Neil Fox, and Kearsy Cormier. 2022. Segmentation of Signs for Research Purposes: Comparing Humans and Machines. In Proceedings of the LREC2022 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources, pages 198–201, Marseille, France. European Language Resources Association.
Cite (Informal):
Segmentation of Signs for Research Purposes: Comparing Humans and Machines (Woll et al., SignLang 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2022.signlang-1.31.pdf
PDF Search