# Zero-shot Text-to-SQL Learning with Auxiliary Task

arXiv: https://arxiv.org/abs/1908.11052 · HTML: https://mlsanity.com/paper/1908.11052/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2019.

## Built on by (most cited first, 10 of 10)

- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect](https://mlsanity.com/paper/2208.10099/) (2022)
- [Reliable Text-to-SQL with Adaptive Abstention](https://mlsanity.com/paper/2501.10858/) (2025)
- [Deep Learning Driven Natural Languages Text to SQL Query Conversion: A Survey](https://mlsanity.com/paper/2208.04415/) (2022)
- [Few-Shot Semantic Parsing for New Predicates](https://mlsanity.com/paper/2101.10708/) (2021)
- [Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing](https://mlsanity.com/paper/2210.01425/) (2022)
- [Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing](https://mlsanity.com/paper/2310.04801/) (2023)
- [Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning](https://mlsanity.com/paper/2109.05395/) (2021)
- [Code Generation for Unknown Libraries via Reading API Documentations](https://mlsanity.com/paper/2202.07806/) (2022)
- [Extreme Multi-label Completion for Semantic Document Labelling with Taxonomy-Aware Parallel Learning](https://mlsanity.com/paper/2412.13809/) (2024)

## Abstract (arXiv)

Recent years have seen great success in the use of neural seq2seq models on the text-to-SQL task. However, little work has paid attention to how these models generalize to realistic unseen data, which naturally raises a question: does this impressive performance signify a perfect generalization model, or are there still some limitations? In this paper, we first diagnose the bottleneck of text-to-SQL task by providing a new testbed, in which we observe that existing models present poor generalization ability on rarely-seen data. The above analysis encourages us to design a simple but effective auxiliary task, which serves as a supportive model as well as a regularization term to the generation task to increase the models generalization. Experimentally, We evaluate our models on a large text-to-SQL dataset WikiSQL. Compared to a strong baseline coarse-to-fine model, our models improve over the baseline by more than 3% absolute in accuracy on the whole dataset. More interestingly, on a zero-shot subset test of WikiSQL, our models achieve 5% absolute accuracy gain over the baseline, clearly demonstrating its superior generalizability.