Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2021
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910671262711808 |
|---|---|
| author | Cui, Yiming Zhang, Wei-Nan Che, Wanxiang Liu, Ting Chen, Zhigang Wang, Shijin |
| author_facet | Cui, Yiming Zhang, Wei-Nan Che, Wanxiang Liu, Ting Chen, Zhigang Wang, Shijin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2108_11574 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models Cui, Yiming Zhang, Wei-Nan Che, Wanxiang Liu, Ting Chen, Zhigang Wang, Shijin Computation and Language Artificial Intelligence 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. |
| title | Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2108.11574 |