Enhancing SPARQL Query Generation for Knowledge Base Question Answering Systems by Learning to Correct Triplets

• Published in: Applied sciences Vol. 14; no. 4; p. 1521
• Main Authors: Qi, Jiexing, Su, Chang, Guo, Zhixin, Wu, Lyuwen, Shen, Zanwei, Fu, Luoyi, Wang, Xinbing, Zhou, Chenghu
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.02.2024
• Subjects: Accuracy; Datasets; further pretraining; Information retrieval; Knowledge; Knowledge Base Question Answering; Language; Methods; Natural language; Queries; semantic parsing; Semantic web; Semantics; Text-to-SPARQL; Triplet Structure
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app14041521

Generating SPARQL queries from natural language questions is challenging in Knowledge Base Question Answering (KBQA) systems. The current state-of-the-art models heavily rely on fine-tuning pretrained models such as T5. However, these methods still encounter critical issues such as triple-flip errors (e.g., (subject, relation, object) is predicted as (object, relation, subject)). To address this limitation, we introduce TSET (Triplet Structure Enhanced T5), a model with a novel pretraining stage positioned between the initial T5 pretraining and the fine-tuning for the Text-to-SPARQL task. In this intermediary stage, we introduce a new objective called Triplet Structure Correction (TSC) to train the model on a SPARQL corpus derived from Wikidata. This objective aims to deepen the model’s understanding of the order of triplets. After this specialized pretraining, the model undergoes fine-tuning for SPARQL query generation, augmenting its query-generation capabilities. We also propose a method named “semantic transformation” to fortify the model’s grasp of SPARQL syntax and semantics without compromising the pre-trained weights of T5. Experimental results demonstrate that our proposed TSET outperforms existing methods on three well-established KBQA datasets: LC-QuAD 2.0, QALD-9 plus, and QALD-10, establishing a new state-of-the-art performance (95.0% F1 and 93.1% QM on LC-QuAD 2.0, 75.85% F1 and 61.76% QM on QALD-9 plus, 51.37% F1 and 40.05% QM on QALD-10).