Papers › TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation

TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation

25 Apr 2018NAACL 2018 6arXiv:1804.09769archive 2025-07-28

Tao Yu, Zifan Li, Zilin Zhang, Rui Zhang, Dragomir Radev

Interacting with relational databases through natural language helps users of any background easily query and analyze a vast amount of data. This requires a system that understands users' questions and converts them to SQL queries automatically. In this paper we present a novel approach, TypeSQL, which views this problem as a slot filling task. Additionally, TypeSQL utilizes type information to better understand rare entities and numbers in natural language questions. We test this idea on the WikiSQL dataset and outperform the prior state-of-the-art by 5.5% in much less time. We also show that accessing the content of databases can significantly improve the performance when users' queries are not well-formed. TypeSQL gets 82.6% accuracy, a 17.5% absolute improvement compared to the previous content-sensitive model.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

taoyds/typesql officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Slot FillingText to SQLText-To-SQLVocal Bursts Type Predictionslot-filling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation WikiSQL TypeSQL+TC (Yu et al., 2018)+ Execution Accuracy 82.6 #2 of 10 Archive leaderboard report
Code Generation WikiSQL TypeSQL (Yu et al., 2018) Execution Accuracy 73.5 #6 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections