ConDA: state-based data augmentation for context-dependent text-to-SQL

• Published in: International journal of machine learning and cybernetics Vol. 15; no. 8; pp. 3157 - 3168
• Main Authors: Wang, Dingzirui, Dou, Longxu, Che, Wanxiang, Wang, Jiaqi, Liu, Jinbo, Li, Lixin, Shang, Jingan, Tao, Lei, Zhang, Jie, Fu, Cong, Song, Xuri
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.08.2024; Springer Nature B.V
• Subjects: Annotations; Artificial Intelligence; Complex Systems; Computational Intelligence; Context; Control; Data augmentation; Datasets; Effectiveness; Engineering; Mechatronics; Methods; Original Article; Pattern Recognition; Performance evaluation; Query languages; Robotics; Semantics; Systems Biology; Context-dependent text-to-SQL; Semantic parsing; Data augmentation; Natural language processing
• ISSN: 1868-8071; 1868-808X
• DOI: 10.1007/s13042-023-02086-z

The context-dependent text-to-SQL task has profound real-world implications, as it facilitates users in extracting knowledge from vast databases, which allows users to acquire the information interactively for better accuracy. Unfortunately, current models struggle to address this task effectively due to the scarcity of data led by the high annotation overhead. The most straightforward method for addressing this problem is data augmentation, which aims at scaling up the parsing corpus. However, the naive methods suffer from the low diversity of the augmented data. To address this limitation, we propose the state-based CON text-dependent text-to-SQL D ata A ugmentation ( ConDA ), which generate and filter augmented data based on the dialogue state, which has higher diversity. Experimental results show that ConDA yields performance improvement on all experimental datasets with an average boosting of 1.6 % , proving the effectiveness of our method.