WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language

TL;DR

This paper introduces WLASL-LEX, a large-scale dataset for recognizing phonological properties in American Sign Language, and evaluates neural network approaches for automatic recognition, demonstrating promising results even on unseen signs.

Contribution

The paper presents a new dataset for phonological sign recognition and an empirical study on end-to-end and feature-based neural methods for this task.

Findings

Graph-based neural networks can recognize phonological properties from skeleton features.

Models perform reasonably well on signs not seen during training.

The dataset enables future research in sign language phonology recognition.

Abstract

Signed Language Processing (SLP) concerns the automated processing of signed languages, the main means of communication of Deaf and hearing impaired individuals. SLP features many different tasks, ranging from sign recognition to translation and production of signed speech, but has been overlooked by the NLP community thus far. 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.