# Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning

arXiv: https://arxiv.org/abs/1909.05438 · HTML: https://mlsanity.com/paper/1909.05438/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2019.

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

- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [Complex Knowledge Base Question Answering: A Survey](https://mlsanity.com/paper/2108.06688/) (2021)
- [A Survey on Neural-symbolic Learning Systems](https://mlsanity.com/paper/2111.08164/) (2021)
- [From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding](https://mlsanity.com/paper/2106.06228/) (2021)
- [Meta-Learning a Cross-lingual Manifold for Semantic Parsing](https://mlsanity.com/paper/2209.12577/) (2022)
- [kFolden: k-Fold Ensemble for Out-Of-Distribution Detection](https://mlsanity.com/paper/2108.12731/) (2021)
- [Knowledge-Aware Meta-learning for Low-Resource Text Classification](https://mlsanity.com/paper/2109.04707/) (2021)
- [WildQA: In-the-Wild Video Question Answering](https://mlsanity.com/paper/2209.06650/) (2022)
- [Few-Shot Semantic Parsing for New Predicates](https://mlsanity.com/paper/2101.10708/) (2021)
- [A Novel Neural-symbolic System under Statistical Relational Learning](https://mlsanity.com/paper/2309.08931/) (2023)

## Abstract (arXiv)

Neural semantic parsing has achieved impressive results in recent years, yet its success relies on the availability of large amounts of supervised data. Our goal is to learn a neural semantic parser when only prior knowledge about a limited number of simple rules is available, without access to either annotated programs or execution results. Our approach is initialized by rules, and improved in a back-translation paradigm using generated question-program pairs from the semantic parser and the question generator. A phrase table with frequent mapping patterns is automatically derived, also updated as training progresses, to measure the quality of generated instances. We train the model with model-agnostic meta-learning to guarantee the accuracy and stability on examples covered by rules, and meanwhile acquire the versatility to generalize well on examples uncovered by rules. Results on three benchmark datasets with different domains and programs show that our approach incrementally improves the accuracy. On WikiSQL, our best model is comparable to the SOTA system learned from denotations.