mlsanityData to 7 Oct 2026

Code Generation as a Dual Task of Code Summarization

arXiv 1910.05923 ↗First posted 14 Oct 2019cs.LG cs.AI cs.SEcited by 62

Not on the map. Why?

Abstract (arXiv)

Code summarization (CS) and code generation (CG) are two crucial tasks in the field of automatic software development. Various neural network-based approaches are proposed to solve these two tasks separately. However, there exists a specific intuitive correlation between CS and CG, which have not been exploited in previous work. In this paper, we apply the relations between two tasks to improve the performance of both tasks. In other words, exploiting the duality between the two tasks, we propose a dual training framework to train the two tasks simultaneously. In this framework, we consider the dualities on probability and attention weights, and design corresponding regularization terms to constrain the duality. We evaluate our approach on two datasets collected from GitHub, and experimental results show that our dual framework can improve the performance of CS and CG tasks over baselines.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 21; 2022: 14; 2023: 13; 2024: 10; 2025: 2; 2026: 1.

62 papers.

Sort:

By area:

  1. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  2. 2021Retrieval Augmented Code Generation and Summarizationcited by 148
  3. 2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 105
  4. 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 89
  5. 2023Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)cited by 72
  6. 2023Is ChatGPT the Ultimate Programming Assistant -- How far is it?cited by 72
  7. 2022Out of the BLEU: how should we assess quality of the Code Generation models?cited by 65
  8. 2021On the Evaluation of Neural Code Summarizationcited by 47
  9. 2022Compilable Neural Code Generation with Compiler Feedbackcited by 46
  10. 2021Multilingual training for Software Engineeringcited by 43
  11. 2021Neural-Symbolic Solver for Math Word Problems with Auxiliary Taskscited by 38
  12. 2023Learning Deep Semantics for Test Completioncited by 31
38 more
  1. 2021CodeQA: A Question Answering Dataset for Source Code Comprehensioncited by 30
  2. 2021Code Structure Guided Transformer for Source Code Summarizationcited by 29
  3. 2021On Multi-Modal Learning of Editing Source Codecited by 25
  4. 2024Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approachcited by 24
  5. 2021CoDesc: A Large Code-Description Parallel Datasetcited by 23
  6. 2024Unsupervised Evaluation of Code LLMs with Round-Trip Correctnesscited by 23
  7. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  8. 2021Improving Code Summarization with Block-wise Abstract Syntax Tree Splittingcited by 19
  9. 2023Exploring the Robustness of Large Language Models for Solving Programming Problemscited by 16
  10. 2024Prompt-based Code Completion via Multi-Retrieval Augmented Generationcited by 16
  11. 2022An Extractive-and-Abstractive Framework for Source Code Summarizationcited by 15
  12. 2023Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approachcited by 15
  13. 2022Source Code Summarization with Structural Relative Position Guided Transformercited by 14
  14. 2021AST-Transformer: Encoding Abstract Syntax Trees Efficiently for Code Summarizationcited by 11
  15. 2021API2Com: On the Improvement of Automatically Generated Code Comments Using API Documentationscited by 10
  16. 2021Improving Tree-Structured Decoder Training for Code Generation via Mutual Learningcited by 10
  17. 2021Exploring Dynamic Selection of Branch Expansion Orders for Code Generationcited by 10
  18. 2022HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representationscited by 9
  19. 2024RACONTEUR: A Knowledgeable, Insightful, and Portable LLM-Powered Shell Command Explainercited by 9
  20. 2026LLMs Corrupt Your Documents When You Delegatecited by 9
  21. 2023Automating Code-Related Tasks Through Transformers: The Impact of Pre-trainingcited by 8
  22. 2022CodePAD: Sequence-based Code Generation with Pushdown Automatoncited by 7
  23. 2023Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarizationcited by 6
  24. 2024Mutation-based Consistency Testing for Evaluating the Code Understanding Capability of LLMscited by 6
  25. 2024ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarizationcited by 6
  26. 2021IOT: Instance-wise Layer Reordering for Transformer Structurescited by 5
  27. 2021Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approachcited by 5
  28. 2021Embedding API Dependency Graph for Neural Code Generationcited by 5
  29. 2021Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal informationcited by 5
  30. 2022GypSum: Learning Hybrid Representations for Code Summarizationcited by 5
  31. 2023Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Controlcited by 5
  32. 2023LUNA: A Model-Based Universal Analysis Framework for Large Language Modelscited by 4
  33. 2025ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Groundingcited by 4
  34. 2021GN-Transformer: Fusing Sequence and Graph Representation for Improved Code Summarizationcited by 3
  35. 2022A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspectivecited by 3
  36. 2022A Survey on Natural Language Processing for Programmingcited by 3
  37. 2023Revisiting File Context for Source Code Summarizationcited by 3
  38. 2024CSA-Trans: Code Structure Aware Transformer for ASTcited by 3

50 most cited of 62 All 62 (JSON)