EUVIMEDEUVIMED entdecken
Crossref

Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing

Jinyang Li, Binyuan Hui, Reynold Cheng, Bowen Qin, Chenhao Ma, Nan Huo, Fei Huang, Wenyu Du, Luo Si, Yongbin Li

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (11) · 13076-13084

DOI: 10.1609/aaai.v37i11.26536 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Jinyang Li und 9 weiteren Autor:innen. Die Arbeit wurde bisher 85-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The task of text-to-SQL parsing, which aims at converting natural language questions into executable SQL queries, has garnered increasing attention in recent years. One of the major challenges in text-to-SQL parsing is domain generalization, i.e., how to generalize well to unseen databases. Recently, the pre-trained text-to-text transformer model, namely T5, though not specialized for text-to-SQL parsing, has achieved state-of-the-art performance on standard benchmarks targeting domain generalization. In this work, we explore ways to further augment the pre-trained T5 model with specialized components for text-to-SQL parsing. Such components are expected to introduce structural inductive bias into text-to-SQL parsers thus improving the model’s capacity on (potentially multi-hop) reasoning, which is critical for generating structure-rich SQLs. To this end, we propose a new architecture GRAPHIX-T5, a mixed model with the standard pre-trained transformer model augmented by specially-designed graph-aware layers. Extensive experiments and analysis demonstrate the effectiveness of GRAPHIX-T5 across four text-to-SQL benchmarks: SPIDER, SYN, REALISTIC and DK. GRAPHIX-T5 surpasses all other T5-based parsers with a significant margin, achieving new state-of-the-art performance. Notably, GRAPHIX-T5-large reaches performance superior to the original T5-large by 5.7% on exact match (EM) accuracy and 6.6% on execution accuracy (EX). This even outperforms the T5-3B by 1.2% on EM and 1.5% on EX

Zitieren

APA

Li, J., Hui, B., Cheng, R., Qin, B., Ma, C., Huo, N., Huang, F., Du, W., Si, L., & Li, Y. (2023). Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11), 13076-13084. https://doi.org/10.1609/aaai.v37i11.26536

Vancouver

Li J, Hui B, Cheng R, Qin B, Ma C, Huo N, et al. Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(11):13076-13084. doi:10.1609/aaai.v37i11.26536

BibTeX
@article{Li2023,
  author = {Li, Jinyang and Hui, Binyuan and Cheng, Reynold and Qin, Bowen and Ma, Chenhao and Huo, Nan and Huang, Fei and Du, Wenyu and Si, Luo and Li, Yongbin},
  title = {Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {11},
  pages = {13076--13084},
  doi = {10.1609/aaai.v37i11.26536}
}
Kostenlos starten →