Page 370 - 《软件学报》2026年第2期

姬涛 等: AI 赋能的关系型数据库系统研究: 标准化、技术与挑战 849

2021. 1174–1189. [doi: 10.18653/v1/2021.findings-acl.100]
[37] Yin PC, Neubig G, Yih WT, Riedel S. TaBERT: Pretraining for joint understanding of textual and tabular data. In: Proc. of the 58th
Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2020. 8413–8426. [doi:
10.18653/v1/2020.acl-main.745]
[38] Yu T, Wu CS, Lin XV, Wang BL, Tan YC, Yang XY, Radev DR, Socher R, Xiong CM. GraPPa: Grammar-augmented pre-training for
table semantic parsing. In: Proc. of the 9th Int’l Conf. on Learning Representations. OpenReview.net, 2021.
[39] Shi P, Ng P, Wang ZG, Zhu HH, Li AH, Wang J, Nogueira dos Santos C, Xiang B. Learning contextual representations for semantic
parsing with generation-augmented pre-training. In: Proc. of the 35th AAAI Conf. on Artificial Intelligence. AAAI, 2020. 13806–13814.
[doi: 10.1609/aaai.v35i15.17627]
[40] Yan Z, Tang DY, Duan N, Liu SJ, Wang WD, Jiang DX, Zhou M, Li ZJ. Assertion-based QA with question-aware open information
extraction. In: Proc. of the 32nd AAAI Conf. on Artificial Intelligence. New Orleans: AAAI, 2018. 6021–6028. [doi: 10.1609/aaai.v32i1.
12052]
[41] Yu T, Yasunaga M, Yang K, Zhang R, Wang DX, Li ZF, Radev D. SyntaxSQLNet: Syntax tree networks for complex and cross-domain
text-to-SQL task. In: Proc. of the 2018 Conf. on Empirical Methods in Natural Language Processing. Brussels: Association for
Computational Linguistics, 2018. 1653–1663. [doi: 10.18653/v1/D18-1193]
[42] Rubin O, Berant J. SmBoP: Semi-autoregressive bottom-up semantic parsing. In: Proc. of the 2021 Conf. of the North American Chapter
of the Association for Computational Linguistics. Association for Computational Linguistics, 2021. 311–324. [doi: 10.18653/v1/2021.
naacl-main.29]
[43] Dong L, Lapata M. Coarse-to-fine decoding for neural semantic parsing. In: Proc. of the 56th Annual Meeting of the Association for
Computational Linguistics. Melbourne: Association for Computational Linguistics, 2018. 731–742. [doi: 10.18653/v1/P18-1068]
[44] Guo HL, Gao T, Wang F, Ma C. Bidirectional attention for SQL generation. In: Proc. of the 4th IEEE Int’l Conf. on Cloud Computing
and Big Data Analysis. Chengdu: IEEE, 2019. 676–682. [doi: 10.1109/ICCCBDA.2019.8725626]
[45] Wang BL, Titov I, Lapata M. Learning semantic parsers from denotations with latent structured alignments and abstract programs. In:
Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language
Processing. Hong Kong: Association for Computational Linguistics, 2019. 3774–3785. [doi: 10.18653/v1/D19-1391]
[46] Brunner U, Stockinger K. ValueNet: A natural language-to-SQL system that learns from database information. In: Proc. of the 37th
IEEE Int’l Conf. on Data Engineering. Chania: IEEE, 2021. 2177–2182. [doi: 10.1109/ICDE51399.2021.00220]
[47] Gan YJ, Chen XY, Xie JX, Purver M, Woodward JR, Drake J, Zhang QF. Natural SQL: Making SQL easier to infer from natural
language specifications. arXiv:2109.05153, 2021.
[48] Suhr A, Chang MW, Shaw P, Lee K. Exploring unexplored generalization challenges for cross-database semantic parsing. In: Proc. of
the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2020.
8372–8388. [doi: 10.18653/v1/2020.acl-main.742]
[49] Yu T, Zhang R, Yang K, Yasunaga M, Wang DX, Li ZF, Ma J, Li I, Yao QN, Roman S, Zhang ZL, Radev D. Spider: A large-scale
human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task. arXiv:1809.08887, 2019.
[50] Liu AW, Hu XM, Wen LJ, Yu PS. A comprehensive evaluation of ChatGPT’s zero-shot text-to-SQL capability. arXiv:2303.13547,
2023.
[51] Rajkumar N, Li R, Bahdanau D. Evaluating the text-to-SQL capabilities of large language models. arXiv:2204.00498, 2022.
[52] Chang SC, Fosler-Lussier E. Selective demonstrations for cross-domain text-to-SQL. In: Proc. of the 2023 Findings of the Association
for Computational Linguistics. Singapore: Association for Computational Linguistics, 2023. 14174–14189. [doi: 10.18653/v1/2023.
findings-emnlp.944]
[53] Pourreza M, Rafiei D. DTS-SQL: Decomposed text-to-SQL with small large language models. In: Proc. of the 2024 Findings of the
Association for Computational Linguistics. Miami: Association for Computational Linguistics, 2024. 8212–8220. [doi: 10.18653/v1/
2024.findings-emnlp.481]
[54] Pourreza M, Rafiei D. DIN-SQL: Decomposed in-context learning of text-to-SQL with self-correction. In: Proc. of the 37th Int’l Conf.
on Neural Information Processing Systems. New Orleans: Curran Associates Inc., 2023. 1577.
[55] Li ZS, Wang X, Zhao JJ, Yang S, Du GQ, Hu XR, Zhang B, Ye YX, Li ZY, Zhao R, Mao HY. PET-SQL: A prompt-enhanced two-
round refinement of text-to-SQL with cross-consistency. arXiv:2403.09732, 2024.
[56] Fan YK, He ZY, Ren TH, Huang C, Jing YN, Zhang K, Wang XS. Metasql: A generate-then-rank framework for natural language to
SQL translation. In: Proc. of the 40th IEEE Int’l Conf. on Data Engineering. Utrecht: IEEE, 2024. 1765–1778. [doi: 10.1109/
ICDE60146.2024.00143]