# Grounded Adaptation for Zero-shot Executable Semantic Parsing

arXiv: https://arxiv.org/abs/2009.07396 · HTML: https://mlsanity.com/paper/2009.07396/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 30 of 76)

- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations](https://mlsanity.com/paper/2106.01093/) (2021)
- [Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing](https://mlsanity.com/paper/2301.07507/) (2023)
- [OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale](https://mlsanity.com/paper/2503.02240/) (2025)
- [RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL](https://mlsanity.com/paper/2205.06983/) (2022)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [Natural SQL: Making SQL Easier to Infer from Natural Language Specifications](https://mlsanity.com/paper/2109.05153/) (2021)
- [ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought](https://mlsanity.com/paper/2310.17342/) (2023)
- [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)
- [Improving Compositional Generalization with Latent Structure and Data Augmentation](https://mlsanity.com/paper/2112.07610/) (2021)
- [Skill-Based Few-Shot Selection for In-Context Learning](https://mlsanity.com/paper/2305.14210/) (2023)
- [Grounding 'Grounding' in NLP](https://mlsanity.com/paper/2106.02192/) (2021)
- [Learning to Synthesize Data for Semantic Parsing](https://mlsanity.com/paper/2104.05827/) (2021)
- [SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models](https://mlsanity.com/paper/2205.07381/) (2022)
- [ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser](https://mlsanity.com/paper/2104.04689/) (2021)
- [Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM](https://mlsanity.com/paper/2402.11517/) (2024)
- [Evaluating Cross-Domain Text-to-SQL Models and Benchmarks](https://mlsanity.com/paper/2310.18538/) (2023)
- [Importance of Synthesizing High-quality Data for Text-to-SQL Parsing](https://mlsanity.com/paper/2212.08785/) (2022)
- [Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization](https://mlsanity.com/paper/2109.02575/) (2021)
- [Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering](https://mlsanity.com/paper/2108.02866/) (2021)
- [Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation](https://mlsanity.com/paper/2306.08891/) (2023)
- [Selective Demonstrations for Cross-domain Text-to-SQL](https://mlsanity.com/paper/2310.06302/) (2023)
- [Zero-Shot Cross-lingual Semantic Parsing](https://mlsanity.com/paper/2104.07554/) (2021)
- [STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing](https://mlsanity.com/paper/2210.11888/) (2022)
- [S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models](https://mlsanity.com/paper/2310.15147/) (2023)
- [PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation](https://mlsanity.com/paper/2205.12697/) (2022)
- [Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval](https://mlsanity.com/paper/2304.13301/) (2023)

## Abstract (arXiv)

We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycle-consistent examples to adapt the parser. Unlike data-augmentation, which typically synthesizes unverified examples in the training environment, GAZP synthesizes examples in the new environment whose input-output consistency are verified. On the Spider, Sparc, and CoSQL zero-shot semantic parsing tasks, GAZP improves logical form and execution accuracy of the baseline parser. Our analyses show that GAZP outperforms data-augmentation in the training environment, performance increases with the amount of GAZP-synthesized data, and cycle-consistency is central to successful adaptation.