# Learning from Executions for Semantic Parsing

arXiv: https://arxiv.org/abs/2104.05819 · HTML: https://mlsanity.com/paper/2104.05819/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 12 Apr 2021.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [Sequence-to-Sequence Learning as Beam-Search Optimization](https://mlsanity.com/paper/1606.02960/) (2016)
- [Data Recombination for Neural Semantic Parsing](https://mlsanity.com/paper/1606.03622/) (2016)
- [Learning a Neural Semantic Parser from User Feedback](https://mlsanity.com/paper/1704.08760/) (2017)
- [TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation](https://mlsanity.com/paper/1810.02720/) (2018)
- [A Discrete Hard EM Approach for Weakly Supervised Question Answering](https://mlsanity.com/paper/1909.04849/) (2019)
- [A Study of Reinforcement Learning for Neural Machine Translation](https://mlsanity.com/paper/1808.08866/) (2018)
- [SparseMAP: Differentiable Sparse Structured Inference](https://mlsanity.com/paper/1802.04223/) (2018)
- [Robust Text-to-SQL Generation with Execution-Guided Decoding](https://mlsanity.com/paper/1807.03100/) (2018)
- [From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood](https://mlsanity.com/paper/1704.07926/) (2017)
- [Discourse-Aware Neural Rewards for Coherent Text Generation](https://mlsanity.com/paper/1805.03766/) (2018)
- [Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs](https://mlsanity.com/paper/1909.04165/) (2019)
- [StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing](https://mlsanity.com/paper/1806.07832/) (2018)
- [Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity](https://mlsanity.com/paper/2007.01919/) (2020)
- [Cross-domain Semantic Parsing via Paraphrasing](https://mlsanity.com/paper/1704.05974/) (2017)
- [Semantic Parsing with Semi-Supervised Sequential Autoencoders](https://mlsanity.com/paper/1609.09315/) (2016)
- [Neural Semantic Parsing over Multiple Knowledge-bases](https://mlsanity.com/paper/1702.01569/) (2017)

## Built on by (most cited first, 7 of 7)

- [ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback](https://mlsanity.com/paper/2503.19988/) (2025)
- [On The Ingredients of an Effective Zero-shot Semantic Parser](https://mlsanity.com/paper/2110.08381/) (2021)
- [GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation](https://mlsanity.com/paper/2205.12078/) (2022)
- [ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects](https://mlsanity.com/paper/2505.17231/) (2025)
- [SPARQLing Database Queries from Intermediate Question Decompositions](https://mlsanity.com/paper/2109.06162/) (2021)
- [Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing](https://mlsanity.com/paper/2210.01425/) (2022)
- [Weakly-Supervised Questions for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2301.09640/) (2023)

## Abstract (arXiv)

Semantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs, which can be executed against a real-world environment. The expensive annotation of utterance-program pairs has long been acknowledged as a major bottleneck for the deployment of contemporary neural models to real-life applications. In this work, we focus on the task of semi-supervised learning where a limited amount of annotated data is available together with many unlabeled NL utterances. Based on the observation that programs which correspond to NL utterances must be always executable, we propose to encourage a parser to generate executable programs for unlabeled utterances. Due to the large search space of executable programs, conventional methods that use approximations based on beam-search such as self-training and top-k marginal likelihood training, do not perform as well. Instead, we view the problem of learning from executions from the perspective of posterior regularization and propose a set of new training objectives. Experimental results on Overnight and GeoQuery show that our new objectives outperform conventional methods, bridging the gap between semi-supervised and supervised learning.