Abstract
In this paper, we bring to attention the task of modelling the phonology of sign languages. We leverage existing resources to construct a large-scale dataset of American Sign Language signs annotated with six different phonological properties. We then conduct an extensive empirical study to investigate whether data-driven end-to-end and feature-based approaches can be optimised to automatically recognise these properties. We find that, despite the inherent challenges of the task, graph-based neural networks that operate over skeleton features extracted from raw videos are able to succeed at the task to a varying degree. Most importantly, we show that this performance pertains even on signs unobserved during training.
| Original language | English |
|---|---|
| Title of host publication | ACL 2022 60th Annual Meeting of the Association for Computational Linguistics |
| Publication status | Accepted/In press - 24 Feb 2022 |
Fingerprint
Dive into the research topics of 'WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language'. Together they form a unique fingerprint.Projects
-
RAI: Centre for Robotics and Artificial Intelligence
Cangelosi, A., Lennox, B., Weightman, A., Dennis, L., Dixon, C., Fisher, M., Herrmann, G., Dickson, A., Lanzon, A., Stancu, A., Saiani, A., Freitas, A., Nini, A., Voronkov, A., Brass, A., Vijayaraghavan, A., Parslew, B., crowther, W., Grieve, B., Adorno, B., Jay, C., Wang, C. C. L., Todd, C., Soutis, C., Arsene, C., Dresner, D., Barrett, E., Gowen, E., Arvin, F., Podd, F., Brown, G., Reger, G., Cooper, G., Mairs, H., Yin, H., Kinloch, I., Eleftheriou, I., Li, J., Carrasco Gomez, J., Ainsworth, J., Sinha, J., Ozanyan, K., Smith, K., Twomey, K., Margetts, L., Ren, L., Zhang, L., Cordeiro, L., Rattray, M., Bissett, M., Elliot, M., Alvarez, M., Luján, M., Nabawy BSc, MSc, PhD, MRAeS, SMAIAA, FHEA, M., Peek, N., Marjanovic, O., Dorn, O., Dudek, P., Green, P., Connolly, P., Da Silva Bartolo, P. J., Gardner, P., Martin, P., Potluri, V., Curtis, R., Schmidt, R., Banach, R., Batista-Navarro, R. T., Kaski, S., Midson, S., Watson, S., Holm, S., Furber, S., Schlegel, V., Mirihanage, W., Mansell, W., Pan, W., Sampson, W., Sellers, W., Yang, W., Cai, P., Sun, Y., Alharthi, A., Macario Rojas, A., Serhan, B., Yu, C., Abara, D., Lopez Pulgarin, E., Faruq, F., Tavella, F., Semeraro, F., Liu, G., Fang, G., Niu, H., Taylor, H., Zhu, H., Collenette, J., Amano, K., Lo, K. C. J., Raggioli, L., Romeo, M., Ruocco, M., Ghaffari Saadat, M., Walmsley, M., Mubarik, A., Vinanzi, S., Su, Y., Mcaleese, H., Stringer, P., Stoican, R., Ye, R., Kurawa, S. S., Zhang, T., Krywonos, W., Xu, Y., Tian, Y., Henderson, A., Morley, D., Tallentire, J., Clayton, J., Hawthornthwaite, S. & Carlson, J.
Project: Research