Adaptive Bi-directional Attention: Exploring Multi-Granularity Representations for Machine Reading Comprehension

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from the final encoder layer which generates the textitcoarse-grained representations of the source sequences, i.e., passage and question. Previous studies have shown that the representation of source sequence becomes more textitcoarse-grained from textitfine-grained as the encoding layer increases. It is generally believed that with the growing number of layers in deep neural networks, the encoding process will gather relevant information for each location increasingly, resulting in more textitcoarse-grained representations, which adds the likelihood of similarity to other locations (referring to homogeneity). Such a phenomenon will mislead the model to make wrong judgments so as to degrade the performance. To this end, we propose a novel approach called Adaptive Bidirectional Attention, which adaptively exploits the source representations of different levels to the predictor. Experimental results on the benchmark dataset, SQuAD 2.0 demonstrate the effectiveness of our approach, and the results are better than the previous state-of-the-art model by 2.5% EM and 2.3% F1 scores.