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

NAACL 2018 Tao YuZifan LiZilin ZhangRui ZhangDragomir 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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Code Generation WikiSQL TypeSQL+TC (Yu et al., 2018)+ Execution Accuracy 82.6 # 1
Code Generation WikiSQL TypeSQL (Yu et al., 2018) Execution Accuracy 73.5 # 5