A Multi-Attention Matching Model for Multiple-Choice Reading Comprehension

Abstract

The Multi-choice machine reading comprehension, selecting the correct answer in the candidate answers, requires obtaining the interaction semantics between the given passage and the question. In this paper, we propose an end-to-end deep learning model. It employs Bi-GRU to contextually encode passages and question, and specifically models complex interactions between the given passage and the question by six kinds of attention functions, including the concatenated attention, the bilinear attention, the element-wise dot attention, minus attention and bi-directional attentions of Query2Context, Context2Query. Then, we use the multi-level attention transfer reasoning mechanism to focus on further obtaining more accurate comprehensive semantics. To demonstrate the validity of our model, we performed experiments on the large reading comprehension data set RACE. The experimental results show that our model surpasses many state-of-the-art systems on the RACE data set and has good reasoning ability.