Towards Human-level Machine Reading Comprehension: Reasoning and Inference with Multiple Strategies
share
This paper presents a new MRC model that is capable of three key comprehension skills: 1) handling rich variations in question types; 2) understanding potential answer choices; and 3) drawing inference through multiple sentences. The model is based on the proposed MUlti-Strategy Inference for Comprehension (MUSIC) architecture, which is able to dynamically apply different attention strategies to different types of questions on the fly. By incorporating a multi-step inference engine analogous to ReasoNet (Shen et al., 2017), MUSIC can also effectively perform multi-sentence inference in generating answers. Evaluation on the RACE dataset shows that the proposed method significantly outperforms previous state-of-the-art models by 7.5 relative accuracy.
READ FULL TEXT
