Enhancing SPARQL Query Generation for Knowledge Base Question Answering Systems by Learning to Correct Triplets
文献类型：期刊论文
| 作者 | Qi, Jiexing2; Su, Chang2; Guo, Zhixin2; Wu, Lyuwen2; Shen, Zanwei2; Fu, Luoyi2; Wang, Xinbing2; Zhou, Chenghu1,2 |
| 刊名 | APPLIED SCIENCES-BASEL
 |
| 出版日期 | 2024-02-01 |
| 卷号 | 14期号:4页码:19 |
| 关键词 | Knowledge Base Question Answering Text-to-SPARQL semantic parsing further pretraining Triplet Structure |
| DOI | 10.3390/app14041521 |
| 通讯作者 | Fu, Luoyi(yiluofu@sjtu.edu.cn) |
| 英文摘要 | 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). |
| 资助项目 | NSF China |
| WOS研究方向 | Chemistry ; Engineering ; Materials Science ; Physics |
| 语种 | 英语 |
| WOS记录号 | WOS:001168342000001 |
| 出版者 | MDPI |
| 资助机构 | NSF China |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/203188]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Fu, Luoyi |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 2.Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai 200240, Peoples R China |
| 推荐引用方式 GB/T 7714 | Qi, Jiexing,Su, Chang,Guo, Zhixin,et al. Enhancing SPARQL Query Generation for Knowledge Base Question Answering Systems by Learning to Correct Triplets[J]. APPLIED SCIENCES-BASEL,2024,14(4):19. |
| APA | Qi, Jiexing.,Su, Chang.,Guo, Zhixin.,Wu, Lyuwen.,Shen, Zanwei.,...&Zhou, Chenghu.(2024).Enhancing SPARQL Query Generation for Knowledge Base Question Answering Systems by Learning to Correct Triplets.APPLIED SCIENCES-BASEL,14(4),19. |
| MLA | Qi, Jiexing,et al."Enhancing SPARQL Query Generation for Knowledge Base Question Answering Systems by Learning to Correct Triplets".APPLIED SCIENCES-BASEL 14.4(2024):19. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。