Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions

By Naihao Deng, Shuaichen Chang, Peng Shi, Tao Yu, Rui Zhang. 2021

5 citations recorded by the source corpus.

Existing text-to-SQL research only considers complete questions as the input, but lay-users might strive to formulate a complete question. To build a smarter natural language interface to database systems (NLIDB) that also processes incomplete questions, we propose a new task, prefix-to-SQL which takes question prefix from users as the input and predicts the intended SQL. We construct a new benchmark called PAGSAS that contains 124K user question prefixes and the intended SQL for 5 sub-tasks Advising, GeoQuery, Scholar, ATIS, and Spider. Additionally, we propose a new metric SAVE to measure how much effort can be saved by users. Experimental results show that PAGSAS is challenging even for strong baseline models such as T5. As we observe the difficulty of prefix-to-SQL is related to the number of omitted tokens, we incorporate curriculum learning of feeding examples with an increasing number of omitted tokens. This improves scores on various sub-tasks by as much as 9% recall scores on sub-task GeoQuery in PAGSAS.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Natural Language Processing

In Code Generation & Program Synthesis

Citations in the corpus

Execution-Based Evaluation for Open-Domain Code Generation (2022, background): “Potential Benefit of Lexical Match Lexicalbased metrics, on the other hand, could indicate less effort for debugging and interpretation (Deng et al., 2021).”