Affiliations: [a]
College of Computer Science and Engineering, North Minzu University, Yinchuan, China
| [b] The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission, North Minzu University, Yinchuan, China
| [c]
Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China
Correspondence:
[*]
Corresponding author. Xintao Chu, College of Computer Science and Engineering, North Minzu University, Yinchuan, 750021, China. E-mail: [email protected].
Abstract: Due to the polysemy and complexity of the Chinese language, Chinese machine reading comprehension has always been a challenging task. To improve the semantic understanding and robustness of Chinese machine reading comprehension models, we propose a model that utilizes adversarial training algorithms and Permuted Language Model (PERT). Firstly, we employ the PERT pre-training model to embed paragraphs and questions into vector space to obtain corresponding sequential representations. Secondly, we use a multi-head self-attention mechanism to extract key textual information from the sequence and employ a Bi-GRU network to semantically fuse the output feature vectors, aiming to learn deep semantic representations in the text. Finally, we introduce perturbations into the model training process. We achieve this by utilizing adversarial training algorithms such as Fast Gradient Method (FGM) and Projected Gradient Descent (PGD). These algorithms generate adversarial samples to enhance the model’s robustness and stability when facing diverse inputs. We conducted comparative experiments on the publicly available Chinese reading comprehension datasets CMRC2018 and DRCD. The experimental results show that our proposed model has achieved significant improvements in both EM and F1-Score compared to the baseline model. To validate the model’s generalization and robustness, we utilized ChatGPT to construct a scientific dataset that includes a large number of domain-specific terms, sentences with mixed Chinese and English, and complex comprehension tasks. Our model also performed remarkably well on the self-built dataset. In conclusion, the proposed model not only effectively enhances the understanding of semantic information in Chinese text but also demonstrates a certain level of generalization capability.
