SQuADv1.1

To train a question answering model based on machine reading comprehension (MRC), sig- nificant effort is required to prepare annotated training data composed of questions and their answers from contexts. …...

AbstractCurrent textual question answering (QA) models achieve strong performance on in-domain test sets, but often do so by fitting surface-level patterns, so they fail to generalize to out-of-distribution settings. To …...

AbstractUnsupervised question answering is an attractive task due to its independence on labeled data. Previous works usually make use of heuristic rules as well as pre-trained models to construct data …...