Evaluating the Robustness of Machine Reading Comprehension Models to Low Resource Entity Renaming
This work addresses the brittleness of QA models for low-resource regions, but it is incremental as it builds on existing adversarial testing methods.
The study investigated the robustness of machine reading comprehension models to entity renaming, particularly with low-resource entities from Africa, and found that large models perform better than base models on novel entities, with person entities posing the highest challenge.
Question answering (QA) models have shown compelling results in the task of Machine Reading Comprehension (MRC). Recently these systems have proved to perform better than humans on held-out test sets of datasets e.g. SQuAD, but their robustness is not guaranteed. The QA model's brittleness is exposed when evaluated on adversarial generated examples by a performance drop. In this study, we explore the robustness of MRC models to entity renaming, with entities from low-resource regions such as Africa. We propose EntSwap, a method for test-time perturbations, to create a test set whose entities have been renamed. In particular, we rename entities of type: country, person, nationality, location, organization, and city, to create AfriSQuAD2. Using the perturbed test set, we evaluate the robustness of three popular MRC models. We find that compared to base models, large models perform well comparatively on novel entities. Furthermore, our analysis indicates that entity type person highly challenges the MRC models' performance.