A review of public datasets in question answering research
Berkant Barla Cambazoglu, Mark Sanderson, Falk Scholer, Bruce W. Croft · ACM SIGIR Forum · 2020
Recent years have seen an increase in the number of publicly available datasets that are released to foster research in question answering systems. In this work, we survey the available datasets and also provide a simple, multi-faceted classification of those datasets. We further survey the most recent evaluation results that form the current state of the art in question answering research by exploring related research challenges and associated online leaderboards. Finally, we provide a discussion around the existing online challenges and provide a wishlist of datasets whose release could benefit question answering research in the future.