Bidirectional Attention Flow for Machine Comprehension
It addresses the problem of improving reading comprehension for AI systems, representing an incremental advance in attention mechanisms.
The paper tackles machine comprehension by modeling interactions between context and query, introducing the Bi-Directional Attention Flow (BIDAF) network that achieves state-of-the-art results on the SQuAD and CNN/DailyMail datasets.
Machine comprehension (MC), answering a query about a given context paragraph, 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 focus on a small portion of the context and summarize it with a fixed-size vector, couple attentions temporally, and/or 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 bi-directional attention flow mechanism to obtain 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.