The Gap Between Deep Learning and Law: Predicting Employment Notice

Abstract

This study aims to determine whether Natural Language Processing with deep learning models can shed new light on the Canadian calculation system for employment notice. In particular, we investigate whether deep learning can enhance the predictability of notice period, that is, whether it is possible to predict notice period with high accuracy. A major challenge with the classification of reasonable notice is the inconsistency of the case law. As argued by the Ontario Court of Appeal, the process of determining reasonable notice is "more art than science". In a previous study, we assessed the predictability of reasonable notice periods by applying statistical machine learning to a hand-annotated dataset of 850 cases. Building on this past study, this paper utilizes state-of-the-art deep learning models on a free-text summary of cases. We further experiment with a variety of domain adaptations of state-of-the-art pretrained BERT-esque models. Our results appear to show that the domain adaptations of BERT-esque models negatively affected performance. Our best performing model was an out-of-the-box RoBERTa base model which achieved a 69% accuracy using a +/-2 prediction window.