Question answering for Azerbaijani language

INST: L_042Question answering (QA) task intends to answer questions posed by humans in natural language. However, the QA task was not investigated for the Azerbaijani language due to the lack of a dataset. In this study, we introduce AzQuAD: Azerbaijani Question Answering Dataset that contains 5000 question-answer pairs based on Azerbaijani Wikipedia articles. We also experimented the performance of prominent QA and pre-trained models on the AzQuAD