A text matching model based on dynamic multi‐mask and augmented adversarial. Issue 2 (18th October 2022)

• Record Type: Journal Article
• Authors: Zhong, Lin; Zeng, Jun; Yu, Yang; Tao, Hongjin; Jiang, Wenying; Cheng, Luxi
• Other Names: Yu Hui guestEditor.
• Is Part Of: Expert systems. Volume 40:Issue 2(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-10-18
• Subjects: adversarial training -- dynamic multi‐mask -- integrating output -- natural language processing -- text matching; Expert systems (Computer science); 006.33
• DOI: 10.1111/exsy.13165
• Languages: English
• ISSNs: 0266-4720

Abstract

Abstract: The text matching is a basic task of NLP and is important for tasks such as text retrieval, question answering, and so forth. The development of pre‐trained language models has promoted the progress of text matching tasks. However, due to the natural particularity of Chinese characters and expressions, the Chinese text matching tasks still have problems such as word segmentation difficulty, serious semantic loss, and model instability. In this paper, we propose the DAINet model, which includes DMM, AA and IO modules. We use the Dynamic Multi‐Mask module (DMM) to enhance the completeness of word segmentation. Then we use the Augmented Adversarial module (AA) to further extraction of semantic information. Finally, we use the Integrated Output module (IO) for a more stable output. We conducted experiments on LCQMC, BQ and Xiaobu datasets and compared the results with seven strong baseline models. The results showed that DAINet model made great improvement, including improving ACC value of BQ dataset to 86.0 % + 0.8 %, AUC value to 93.9 % + 0.8 %, ACC value of LCQMC dataset to 88.7 % + 1.1 % and AUC value to 97.2 % + 1.0 % . The ACC value of Xiaobu dataset was improved to 83.2 % + 1.3 % and the AUC value was improved to 91.7 % + 2.2 % . Further ablation experiment results show that the proposed DMM, AA and IO modules have good adaptability and improvement over existing models.