BookQA: Stories of Challenges and Opportunities
This work addresses the challenge of high-precision question answering on books, which is important for applications in education and literature analysis, but it is incremental as it builds on existing methods and datasets.
The authors tackled the problem of answering questions about book content (BookQA) using a system that retrieves relevant passages and applies a memory network, achieving significant improvements over baselines with BERT-based retrieval and pretraining on the NarrativeQA corpus.
We present a system for answering questions based on the full text of books (BookQA), which first selects book passages given a question at hand, and then uses a memory network to reason and predict an answer. To improve generalization, we pretrain our memory network using artificial questions generated from book sentences. We experiment with the recently published NarrativeQA corpus, on the subset of Who questions, which expect book characters as answers. We experimentally show that BERT-based retrieval and pretraining improve over baseline results significantly. At the same time, we confirm that NarrativeQA is a highly challenging data set, and that there is need for novel research in order to achieve high-precision BookQA results. We analyze some of the bottlenecks of the current approach, and we argue that more research is needed on text representation, retrieval of relevant passages, and reasoning, including commonsense knowledge.