# Data Recombination for Neural Semantic Parsing

arXiv: https://arxiv.org/abs/1606.03622 · HTML: https://mlsanity.com/paper/1606.03622/

## Key facts

- Cited by 111 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2016.

## Built on by (most cited first, 30 of 111)

- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [Meta-Learning to Compositionally Generalize](https://mlsanity.com/paper/2106.04252/) (2021)
- [Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text](https://mlsanity.com/paper/2307.07696/) (2023)
- [Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations](https://mlsanity.com/paper/2104.07478/) (2021)
- [Neural Data Augmentation via Example Extrapolation](https://mlsanity.com/paper/2102.01335/) (2021)
- [Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing](https://mlsanity.com/paper/2205.12253/) (2022)
- [Improving Compositional Generalization with Latent Structure and Data Augmentation](https://mlsanity.com/paper/2112.07610/) (2021)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [ELLA: Exploration through Learned Language Abstraction](https://mlsanity.com/paper/2103.05825/) (2021)
- [An Investigation of the (In)effectiveness of Counterfactually Augmented Data](https://mlsanity.com/paper/2107.00753/) (2021)
- [Learning to Synthesize Data for Semantic Parsing](https://mlsanity.com/paper/2104.05827/) (2021)
- [Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks](https://mlsanity.com/paper/2107.01431/) (2021)
- [SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models](https://mlsanity.com/paper/2205.07381/) (2022)
- [Communicating Natural Programs to Humans and Machines](https://mlsanity.com/paper/2106.07824/) (2021)
- [Controllable Semantic Parsing via Retrieval Augmentation](https://mlsanity.com/paper/2110.08458/) (2021)
- [Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing](https://mlsanity.com/paper/2103.02227/) (2021)
- [Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models](https://mlsanity.com/paper/2308.00304/) (2023)
- [Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback](https://mlsanity.com/paper/1805.01252/) (2018)
- [HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization](https://mlsanity.com/paper/2106.00149/) (2021)
- [Sequence-to-Sequence Learning with Latent Neural Grammars](https://mlsanity.com/paper/2109.01135/) (2021)
- [Disentangled Sequence to Sequence Learning for Compositional Generalization](https://mlsanity.com/paper/2110.04655/) (2021)
- [Lexicon Learning for Few-Shot Neural Sequence Modeling](https://mlsanity.com/paper/2106.03993/) (2021)
- [Importance of Synthesizing High-quality Data for Text-to-SQL Parsing](https://mlsanity.com/paper/2212.08785/) (2022)
- [SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising](https://mlsanity.com/paper/2105.07911/) (2021)
- [Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization](https://mlsanity.com/paper/2109.02575/) (2021)

## Abstract (arXiv)

Modeling crisp logical regularities is crucial in semantic parsing, making it difficult for neural models with no task-specific prior knowledge to achieve good results. In this paper, we introduce data recombination, a novel framework for injecting such prior knowledge into a model. From the training data, we induce a high-precision synchronous context-free grammar, which captures important conditional independence properties commonly found in semantic parsing. We then train a sequence-to-sequence recurrent network (RNN) model with a novel attention-based copying mechanism on datapoints sampled from this grammar, thereby teaching the model about these structural properties. Data recombination improves the accuracy of our RNN model on three semantic parsing datasets, leading to new state-of-the-art performance on the standard GeoQuery dataset for models with comparable supervision.