# Meta-Learning for Domain Generalization in Semantic Parsing

arXiv: https://arxiv.org/abs/2010.11988 · HTML: https://mlsanity.com/paper/2010.11988/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 30 of 41)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Meta-Learning to Compositionally Generalize](https://mlsanity.com/paper/2106.04252/) (2021)
- [A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions](https://mlsanity.com/paper/2208.13629/) (2022)
- [Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect](https://mlsanity.com/paper/2208.10099/) (2022)
- [Learning to Synthesize Data for Semantic Parsing](https://mlsanity.com/paper/2104.05827/) (2021)
- [S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers](https://mlsanity.com/paper/2203.06958/) (2022)
- [PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization](https://mlsanity.com/paper/2212.00979/) (2022)
- [Controllable Semantic Parsing via Retrieval Augmentation](https://mlsanity.com/paper/2110.08458/) (2021)
- [Anomaly Detection under Distribution Shift](https://mlsanity.com/paper/2303.13845/) (2023)
- [Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing](https://mlsanity.com/paper/2206.14017/) (2022)
- [Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition](https://mlsanity.com/paper/2206.06629/) (2022)
- [GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalization](https://mlsanity.com/paper/2211.02733/) (2022)
- [Domain Generalization through Meta-Learning: A Survey](https://mlsanity.com/paper/2404.02785/) (2024)
- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms](https://mlsanity.com/paper/2106.00925/) (2021)
- [Reliable Text-to-SQL with Adaptive Abstention](https://mlsanity.com/paper/2501.10858/) (2025)
- [Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge](https://mlsanity.com/paper/2301.01067/) (2023)
- [ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis](https://mlsanity.com/paper/2307.13883/) (2023)
- [Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning](https://mlsanity.com/paper/2407.03227/) (2024)
- [Meta-Learning a Cross-lingual Manifold for Semantic Parsing](https://mlsanity.com/paper/2209.12577/) (2022)
- [Compositional Generalization and Decomposition in Neural Program Synthesis](https://mlsanity.com/paper/2204.03758/) (2022)
- [Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer](https://mlsanity.com/paper/2107.09840/) (2021)
- [Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization](https://mlsanity.com/paper/2606.21736/) (2026)
- [Code Generation for Unknown Libraries via Reading API Documentations](https://mlsanity.com/paper/2202.07806/) (2022)
- [Meta-learning For Vision-and-language Cross-lingual Transfer](https://mlsanity.com/paper/2305.14843/) (2023)
- [AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images](https://mlsanity.com/paper/2312.06106/) (2023)

## Abstract (arXiv)

The importance of building semantic parsers which can be applied to new domains and generate programs unseen at training has long been acknowledged, and datasets testing out-of-domain performance are becoming increasingly available. However, little or no attention has been devoted to learning algorithms or objectives which promote domain generalization, with virtually all existing approaches relying on standard supervised learning. In this work, we use a meta-learning framework which targets zero-shot domain generalization for semantic parsing. We apply a model-agnostic training algorithm that simulates zero-shot parsing by constructing virtual train and test sets from disjoint domains. The learning objective capitalizes on the intuition that gradient steps that improve source-domain performance should also improve target-domain performance, thus encouraging a parser to generalize to unseen target domains. Experimental results on the (English) Spider and Chinese Spider datasets show that the meta-learning objective significantly boosts the performance of a baseline parser.