# Natural Language to Structured Query Generation via Meta-Learning

arXiv: https://arxiv.org/abs/1803.02400 · HTML: https://mlsanity.com/paper/1803.02400/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2018.

## Built on by (most cited first, 30 of 33)

- [Noisy Channel Language Model Prompting for Few-Shot Text Classification](https://mlsanity.com/paper/2108.04106/) (2021)
- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning](https://mlsanity.com/paper/2206.03996/) (2022)
- [Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect](https://mlsanity.com/paper/2208.10099/) (2022)
- [On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning](https://mlsanity.com/paper/2102.10454/) (2021)
- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [Robust Visual Question Answering: Datasets, Methods, and Future Challenges](https://mlsanity.com/paper/2307.11471/) (2023)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning](https://mlsanity.com/paper/2105.12995/) (2021)
- [Few Shot Dialogue State Tracking using Meta-learning](https://mlsanity.com/paper/2101.06779/) (2021)
- [On Robustness of Neural Semantic Parsers](https://mlsanity.com/paper/2102.01563/) (2021)
- [Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errors](https://mlsanity.com/paper/2501.09310/) (2025)
- [Multi-modal Program Inference: a Marriage of Pre-trainedLanguage Models and Component-based Synthesis](https://mlsanity.com/paper/2109.02445/) (2021)
- [Meta-Learning a Cross-lingual Manifold for Semantic Parsing](https://mlsanity.com/paper/2209.12577/) (2022)
- [Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing](https://mlsanity.com/paper/2104.04736/) (2021)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [kFolden: k-Fold Ensemble for Out-Of-Distribution Detection](https://mlsanity.com/paper/2108.12731/) (2021)
- [WildQA: In-the-Wild Video Question Answering](https://mlsanity.com/paper/2209.06650/) (2022)
- [ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification](https://mlsanity.com/paper/2101.11753/) (2021)
- [ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback](https://mlsanity.com/paper/2107.14035/) (2021)
- [Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes](https://mlsanity.com/paper/2302.11709/) (2023)
- [Few-Shot Semantic Parsing for New Predicates](https://mlsanity.com/paper/2101.10708/) (2021)
- [SPARQLing Database Queries from Intermediate Question Decompositions](https://mlsanity.com/paper/2109.06162/) (2021)
- [Set-to-Sequence Methods in Machine Learning: a Review](https://mlsanity.com/paper/2103.09656/) (2021)
- [DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks](https://mlsanity.com/paper/2101.04226/) (2021)
- [Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning](https://mlsanity.com/paper/2109.05395/) (2021)
- [Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems](https://mlsanity.com/paper/2312.15340/) (2023)
- [xDBTagger: Explainable Natural Language Interface to Databases Using Keyword Mappings and Schema Graph](https://mlsanity.com/paper/2210.03768/) (2022)
- [Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning](https://mlsanity.com/paper/2211.15180/) (2022)
- [ERATTA: Extreme RAG for Table To Answers with Large Language Models](https://mlsanity.com/paper/2405.03963/) (2024)

## Abstract (arXiv)

In conventional supervised training, a model is trained to fit all the training examples. However, having a monolithic model may not always be the best strategy, as examples could vary widely. In this work, we explore a different learning protocol that treats each example as a unique pseudo-task, by reducing the original learning problem to a few-shot meta-learning scenario with the help of a domain-dependent relevance function. When evaluated on the WikiSQL dataset, our approach leads to faster convergence and achieves 1.1%-5.4% absolute accuracy gains over the non-meta-learning counterparts.