Leveraging Unannotated Data to Improve Zero-Shot Question Answering in the French Legal Domain

State of the art question answering models have recently shown impressive performance especially in a zero-shot setup. This approach is particularly useful when confronted with a highly diverse domain such as the legal field, in which it is increasingly difficult to have a dataset covering every notion and concept. In this work, we propose a flexible generative question answering approach to contract analysis as well as a weakly supervised procedure to leverage non-annotated data and boost our models’ performance in general, and their zero-shot performance in particular.