Causal Intervention for Mitigating Name Bias in Machine Reading Comprehension

Jiazheng Zhu, Shaojuan Wu, Xiaowang Zhang, Yuexian Hou, Zhiyong Feng

Abstract
Machine Reading Comprehension (MRC) is to answer questions based on a given passage, which has made great achievements using pre-trained Language Models (LMs). We study the robustness of MRC models to names which is flexible and repeatability. MRC models based on LMs may overuse the name information to make predictions, which causes the representation of names to be non-interchangeable, called name bias. In this paper, we propose a novel Causal Interventional paradigm for MRC (CI4MRC) to mitigate name bias. Specifically, we uncover that the pre-trained knowledge concerning names is indeed a confounder by analyzing the causalities among the pre-trained knowledge, context representation and answers based on a Structural Causal Model (SCM). We develop effective CI4MRC algorithmic implementations to constrain the confounder based on the neuron-wise and token-wise adjustments. Experiments demonstrate that our proposed CI4MRC effectively mitigates the name bias and achieves competitive performance on the original SQuAD. Moreover, our method is general to various pre-trained LMs and performs robustly on the adversarial datasets.
Anthology ID:
2023.findings-acl.812
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12837–12852
Language:
URL:
https://aclanthology.org/2023.findings-acl.812
DOI:
10.18653/v1/2023.findings-acl.812
Bibkey:
Cite (ACL):
Jiazheng Zhu, Shaojuan Wu, Xiaowang Zhang, Yuexian Hou, and Zhiyong Feng. 2023. Causal Intervention for Mitigating Name Bias in Machine Reading Comprehension. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12837–12852, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Causal Intervention for Mitigating Name Bias in Machine Reading Comprehension (Zhu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-acl.812.pdf
PDF Search