Multilingual Multi-aspect Explainability Analyses On Machine Reading Comprehension Models

Cui Yiming, Zhang Wei-nan, Che Wanxiang, Liu Ting, Chen Zhigang, Wang Shijin. iScience 2021

[Paper]    
Applications Attention Mechanism Interpretability And Explainability Model Architecture Security TACL Transformer

Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts remains unclear, placing an obstacle for further understanding these models. This paper focuses on conducting a series of analytical experiments to examine the relations between the multi-head self-attention and the final MRC system performance, revealing the potential explainability in PLM-based MRC models. To ensure the robustness of the analyses, we perform our experiments in a multilingual way on top of various PLMs. We discover that passage-to-question and passage understanding attentions are the most important ones in the question answering process, showing strong correlations to the final performance than other parts. Through comprehensive visualizations and case studies, we also observe several general findings on the attention maps, which can be helpful to understand how these models solve the questions.

Similar Work