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
Abstract
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
BibTeX
@article{Li_Hui_Cheng_Qin_Ma_Huo_Huang_Du_Si_Li_2023, title={Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26536}, DOI={10.1609/aaai.v37i11.26536}, abstractNote={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}, number={11}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, 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}, year={2023}, month={Jun.}, pages={13076-13084} }