mlsanityData to 7 Oct 2026

Program Synthesis and Semantic Parsing with Learned Code Idioms

arXiv 1906.10816 ↗First posted 26 Jun 2019cs.LG cs.AI cs.CLcited by 34

Not on the map. Why?

Abstract (arXiv)

Program synthesis of general-purpose source code from natural language specifications is challenging due to the need to reason about high-level patterns in the target program and low-level implementation details at the same time. In this work, we present PATOIS, a system that allows a neural program synthesizer to explicitly interleave high-level and low-level reasoning at every generation step. It accomplishes this by automatically mining common code idioms from a given corpus, incorporating them into the underlying language for neural synthesis, and training a tree-based neural synthesizer to use these idioms during code generation. We evaluate PATOIS on two complex semantic parsing datasets and show that using learned code idioms improves the synthesizer's accuracy.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 6; 2024: 6; 2025: 2; 2026: 1.

34 papers.

Sort:

By area:

  1. 2025Inducing Programmatic Skills for Agentic Taskscited by 103
  2. 2024Symbolic Regression with a Learned Concept Librarycited by 76
  3. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 70
  4. 2022Top-Down Synthesis for Library Learningcited by 57
  5. 2023LILO: Learning Interpretable Libraries by Compressing and Documenting Codecited by 46
  6. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 44
  7. 2024Securing Large Language Models: Threats, Vulnerabilities and Responsible Practicescited by 36
  8. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  9. 2022A Hazard Analysis Framework for Code Synthesis Large Language Modelscited by 22
  10. 2021Investigating Math Word Problems using Pretrained Multilingual Language Modelscited by 21
  11. 2021Improving Tree-Structured Decoder Training for Code Generation via Mutual Learningcited by 10
  12. 2021Exploring Dynamic Selection of Branch Expansion Orders for Code Generationcited by 10
22 more
  1. 2023R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intentscited by 10
  2. 2021Total Recall: a Customized Continual Learning Method for Neural Semantic Parserscited by 9
  3. 2022On the Effectiveness of Pretrained Models for API Learningcited by 9
  4. 2023CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Codecited by 9
  5. 2021Toward Code Generation: A Survey and Lessons from Semantic Parsingcited by 8
  6. 2022A Simple, Yet Effective Approach to Finding Biases in Code Generationcited by 8
  7. 2021Transcribing Natural Languages for The Deaf via Neural Editing Programscited by 7
  8. 2024On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generationcited by 6
  9. 2022Predictive Querying for Autoregressive Neural Sequence Modelscited by 5
  10. 2021Autoencoders as Tools for Program Synthesiscited by 4
  11. 2024Full Line Code Completion: Bringing AI to Desktopcited by 4
  12. 2025Generating Planning Feedback for Open-Ended Programming Exercises with LLMscited by 4
  13. 2023Neural Machine Translation for Code Generationcited by 3
  14. 2023kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learningcited by 3
  15. 2021Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learningcited by 2
  16. 2023Bayesian Program Learning by Decompiling Amortized Knowledgecited by 2
  17. 2021Procedures as Programs: Hierarchical Control of Situated Agents through Natural Languagecited by 0
  18. 2022Iterative Genetic Improvement: Scaling Stochastic Program Synthesiscited by 0
  19. 2022Antecedent Predictions Are More Important Than You Think: An Effective Method for Tree-Based Code Generationcited by 0
  20. 2022Programming by Example and Text-to-Code Translation for Conversational Code Generationcited by 0
  21. 2024On the Efficient Marginalization of Probabilistic Sequence Modelscited by 0
  22. 2026Prospective Compression in Human Abstraction Learningcited by 0