Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data
This addresses the problem of limited real-world applicability in text-to-SQL systems for researchers and practitioners, though it is incremental as it focuses on dataset creation rather than method innovation.
The authors tackled the lack of real-world diversity in semantic parsing datasets by releasing SEDE, a dataset of 12,023 utterance-SQL pairs from Stack Exchange, which reveals significant performance gaps compared to existing datasets.
Most available semantic parsing datasets, comprising of pairs of natural utterances and logical forms, were collected solely for the purpose of training and evaluation of natural language understanding systems. As a result, they do not contain any of the richness and variety of natural-occurring utterances, where humans ask about data they need or are curious about. In this work, we release SEDE, a dataset with 12,023 pairs of utterances and SQL queries collected from real usage on the Stack Exchange website. We show that these pairs contain a variety of real-world challenges which were rarely reflected so far in any other semantic parsing dataset, propose an evaluation metric based on comparison of partial query clauses that is more suitable for real-world queries, and conduct experiments with strong baselines, showing a large gap between the performance on SEDE compared to other common datasets.