Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

About

Relational structures such as schema linking and schema encoding have been validated as a key component to qualitatively translating natural language into SQL queries. However, introducing these structural relations comes with prices: they often result in a specialized model structure, which largely prohibits using large pretrained models in text-to-SQL. To address this problem, we propose RASAT: a Transformer seq2seq architecture augmented with relation-aware self-attention that could leverage a variety of relational structures while inheriting the pretrained parameters from the T5 model effectively. Our model can incorporate almost all types of existing relations in the literature, and in addition, we propose introducing co-reference relations for the multi-turn scenario. Experimental results on three widely used text-to-SQL datasets, covering both single-turn and multi-turn scenarios, have shown that RASAT could achieve state-of-the-art results across all three benchmarks (75.5% EX on Spider, 52.6% IEX on SParC, and 37.4% IEX on CoSQL).

Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Yu Cheng, Chenghu Zhou, Xinbing Wang, Quanshi Zhang, Zhouhan Lin• 2022

Related benchmarks

TaskDatasetResultRank
Text-to-SQLSpider (test)
Execution Accuracy75.5
213
Text-to-SQLSpider (dev)--
147
Text-to-SQLSpider 1.0 (test)
EM Acc (Overall)70.9
110
Text-to-SQLSpider 1.0 (dev)
Exact Match Accuracy75.3
92
Text-to-SQLSpider-Realistic
Execution Accuracy (EX)71.9
47
Context-dependent Text-to-SQLCoSQL (dev)
Question Match58.8
33
Multi-turn Text-to-SQLSParC In-domain
Exact Match67.7
29
Multi-turn Text-to-SQLCoSQL In-domain
Exact Match58.8
29
Multi-turn Text-to-SQLCoSQL & SParC Aggregate
Avg Exact Match (EM)57.7
29
Context-dependent Text-to-SQLSParC 1.0 (dev)
Question Match67.7
27
Showing 10 of 18 rows

Other info

Code

Follow for update