On the Robustness of Reading Comprehension Models to Entity Renaming

Anonymous

Abstract: We study the robustness of machine reading comprehension (MRC) models to entity renaming---do models make more wrong predictions when answer entities have different names? Such failures imply that models overly rely on entity information to answer questions, and thus may generalize poorly when facts about the world change or questions are asked about novel entities. To systematically audit this issue, we present a general and scalable pipeline to replace entity names with names from a variety of sources, ranging from common English names to names from other languages to arbitrary strings. Across five datasets and three pretrained model architectures, MRC models consistently perform worse when entities are renamed, with particularly large accuracy drops on datasets constructed via distant supervision. We also find large differences between models: SpanBERT, which is pretrained with span-level masking, is more robust than RoBERTa, despite having similar accuracy on unperturbed test data. We further experiment with different masking strategies as the continual pretraining objective and find that entity-based masking can improve the robustness of MRC models.