Machine Comprehension (MC), answering a query about a given context, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use attention to summarize the context (or query) into a single vector, couple attentions temporally, and often form a uni-directional attention. In this paper we introduce the Bi-directional Attention Flow (BiDAF) network, a multi-stage hierarchical process that represents the context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization. Our experimental evaluations show that our model achieves the state-of-the-art results in Stanford Question Answering Dataset (SQuAD) and CNN/DailyMail Cloze Test.
View on arXiv