Xiangyang Mou author Mo Yu author Bingsheng Yao author Chenghao Yang author Xiaoxiao Guo author Saloni Potdar author Hui Su author 2020-jul text Association for Computational Linguistics Online conference publication A lot of progress has been made to improve question answering (QA) in recent years, but the special problem of QA over narrative book stories has not been explored in-depth. We formulate BookQA as an open-domain QA task given its similar dependency on evidence retrieval. We further investigate how state-of-the-art open-domain QA approaches can help BookQA. Besides achieving state-of-the-art on the NarrativeQA benchmark, our study also reveals the difficulty of evidence retrieval in books with a wealth of experiments and analysis - which necessitates future effort on novel solutions for evidence retrieval in BookQA. mou-etal-2020-frustratingly https://www.aclweb.org/anthology/2020.nuse-1.13 2020-jul 108 113