Text-to-SQL task maps natural language utterances to structured queries that can be issued to a database. State-of-the-art (SOTA) systems rely on finetuning large, pre-trained language models in conjunction with constrained decoding applying a SQL parser. On the well established Spider dataset, we begin with Oracle studies: specifically, choosing an Oracle hypothesis from a SOTA model's 10-best list, yields a 7.7% absolute improvement in both exact match (EM) and execution (EX) accuracy, showing significant potential improvements with reranking. Identifying coherence and correctness as reranking approaches, we design a model generating a query plan and propose a heuristic schema linking algorithm. Combining both approaches, with T5-Large, we obtain a consistent 1% improvement in EM accuracy, and a 2.5% improvement in EX, establishing a new SOTA for this task. Our comprehensive error studies on DEV data show the underlying difficulty in making progress on this task.
@article{arxiv.2210.10668,
title = {N-Best Hypotheses Reranking for Text-To-SQL Systems},
author = {Lu Zeng and Sree Hari Krishnan Parthasarathi and Dilek Hakkani-Tur},
journal= {arXiv preprint arXiv:2210.10668},
year = {2022}
}