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

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

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments and analysis demonstrate the effectiveness of GRAPHIX-T5 across four text-to-SQL benchmarks: SPIDER, SYN, REALISTIC and DK. GRAPHIX-T5 surpass all other T5-based parsers with a significant margin, achieving new state-of-the-art performance.
Researcher Affiliation Collaboration 1The University of Hong Kong 2DAMO Academy, Alibaba Group 3Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences 4The Chinese University of Hong Kong (Shenzhen) 5Guangdong Hong Kong-Macau Joint Laboratory
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks (clearly labeled algorithm sections or code-like formatted procedures).
Open Source Code Yes We implement our codes 2 mainly based on hugging-face transformers library (Wolf et al. 2020) 3. 2https://github.com/Alibaba Research/DAMO-Conv AI/tree/ main/graphix
Open Datasets Yes We conduct extensive experiments on four challenging benchmarks for cross-domain text-to SQLs and two different training settings. (1) SPIDER (Yu et al. 2018b) is a large-scale cross-domain text-to-SQL benchmark. ... (2) SYN (Gan et al. 2021a) replaces the simple string-matched question tokens or schema names with their synonyms. (3) DK (Gan, Chen, and Purver 2021) requires the text-to-SQL parsers to equip with the capability of domain knowledge reasoning. (4) REALISTIC removes and switches the obvious mentions of schema items in questions...
Dataset Splits Yes SPIDER (Yu et al. 2018b) is a large-scale cross-domain text-to-SQL benchmark. It contains 8659 training examples and 1034 development examples, which covers 200 complex databases across 138 domains.
Hardware Specification Yes All experiments are conducted on one NVIDIA Tesla A100, which is available for most research centers.
Software Dependencies No The paper mentions using the "hugging-face transformers library (Wolf et al. 2020)" but does not specify a version number for this or any other software dependency.
Experiment Setup Yes We set the max input length as 1024, generation max length as 128, and batch size as 32. We also adopt Adafactor (Shazeer and Stern 2018) as our primary optimizer with a linear decayed learning rate of 5e-5.