mlsanityData to 14 Oct 2026

Abstract Syntax Networks for Code Generation and Semantic Parsing

arXiv 1704.07535 ↗First posted 25 Apr 2017cs.CL cs.AI cs.LGcited by 92

Not on the map. Why?

Abstract (arXiv)

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs are represented as abstract syntax trees (ASTs) and constructed by a decoder with a dynamically-determined modular structure paralleling the structure of the output tree. On the benchmark Hearthstone dataset for code generation, our model obtains 79.2 BLEU and 22.7% exact match accuracy, compared to previous state-of-the-art values of 67.1 and 6.1%. Furthermore, we perform competitively on the Atis, Jobs, and Geo semantic parsing datasets with no task-specific engineering.

Key facts. Cited by 92 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 22; 2022: 20; 2023: 17; 2024: 9; 2025: 14; 2026: 10.

92 papers.

Sort:

By area:

  1. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 239
  2. 2023Efficient Guided Generation for Large Language Modelscited by 200
  3. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
  4. 2022DocPrompting: Generating Code by Retrieving the Docscited by 153
  5. 2021Retrieval Augmented Code Generation and Summarizationcited by 149
  6. 2022Natural Language to Code Translation with Executioncited by 124
  7. 2023Execution-based Code Generation using Deep Reinforcement Learningcited by 99
  8. 2021RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answeringcited by 86
  9. 2023Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Modelscited by 68
  10. 2022Out of the BLEU: how should we assess quality of the Code Generation models?cited by 65
  11. 2023AI-Generated Content (AIGC): A Surveycited by 59
  12. 2021A Syntax-Guided Edit Decoder for Neural Program Repaircited by 57
38 more
  1. 2022Compilable Neural Code Generation with Compiler Feedbackcited by 47
  2. 2021TreeBERT: A Tree-Based Pre-Trained Model for Programming Languagecited by 41
  3. 2022MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languagescited by 41
  4. 2024Automatic Programming: Large Language Models and Beyondcited by 36
  5. 2022StructCoder: Structure-Aware Transformer for Code Generationcited by 34
  6. 2024AST-T5: Structure-Aware Pretraining for Code Generation and Understandingcited by 33
  7. 2025CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debuggingcited by 32
  8. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  9. 2021How could Neural Networks understand Programs?cited by 26
  10. 2024HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agentcited by 24
  11. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  12. 2025An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunitiescited by 18
  13. 2023B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesiscited by 17
  14. 2021Learning Structural Edits via Incremental Tree Transformationscited by 16
  15. 2021Shellcode_IA32: A Dataset for Automatic Shellcode Generationcited by 16
  16. 2023KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repaircited by 13
  17. 2021Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solvingcited by 11
  18. 2022Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generationcited by 11
  19. 2025TreeDiff: AST-Guided Code Generation with Diffusion LLMscited by 11
  20. 2021Improving Tree-Structured Decoder Training for Code Generation via Mutual Learningcited by 10
  21. 2021Exploring Dynamic Selection of Branch Expansion Orders for Code Generationcited by 10
  22. 2025Towards an Understanding of Context Utilization in Code Intelligencecited by 10
  23. 2022On the Effectiveness of Pretrained Models for API Learningcited by 9
  24. 2021Toward Code Generation: A Survey and Lessons from Semantic Parsingcited by 8
  25. 2021Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generationcited by 8
  26. 2021Few-Shot Semantic Parsing for New Predicatescited by 7
  27. 2021Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modelingcited by 7
  28. 2022Paraphrasing Techniques for Maritime QA systemcited by 7
  29. 2022CodePAD: Sequence-based Code Generation with Pushdown Automatoncited by 7
  30. 2022The impact of lexical and grammatical processing on generating code from natural languagecited by 6
  31. 2024mathbbUSCD: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decodingcited by 6
  32. 2025CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routingcited by 6
  33. 2021Robot Program Parameter Inference via Differentiable Shadow Program Inversioncited by 5
  34. 2021Embedding API Dependency Graph for Neural Code Generationcited by 5
  35. 2023Large Language Models Should Ask Clarifying Questions to Increase Confidence in Generated Codecited by 5
  36. 2025Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?cited by 5
  37. 2026CODESTRUCT: Code Agents over Structured Action Spacescited by 5
  38. 2021Autoencoders as Tools for Program Synthesiscited by 4

50 most cited of 92 All 92 (JSON)