Convolutional Encoding in Bidirectional Attention Flow for Question Answering

Deep learning systems for complex natural language processing tasks like question answering are often large, cumbersome models that require excessive computational power and time. We seek to address this issue by exploring efficient and parallelizable alternatives to the more computationally expensive components of one of the top-performing question-answering architectures. In particular, we examine the use of convolutional neural networks as a replacement for the default long-short term memory units used to encode the context and question input text. The architecture we use is a streamlined version of the bidirectional attention flow model by Minjoon Seo at the Allen Institute for Artificial Intelligence.