Feature-augmented Machine Reading Comprehension with Auxiliary Tasks

원문 초록

While most successful approaches for machine reading comprehension rely on single training objective, it is assumed that the encoder layer can learn great representation through the loss function we define in the predict layer, which is cross entropy in most of time, in the case that we first use neural networks to encode the question and paragraph, then directly fuse the encoding result of them. However, due to the distantly loss backpropagating in reading comprehension, the encoder layer cannot learn effectively and be directly supervised. Thus, the encoder layer can not learn the representation well at any time. Base on this, we propose to inject multi granularity information to the encoding layer. Experiments demonstrate the effect of adding multi granularity information to the encoding layer can boost the performance of machine reading comprehension system. Finally, empirical study shows that our approach can be applied to many existing MRC models.