mlsanityData to 14 Oct 2026

code2seq: Generating Sequences from Structured Representations of Code

arXiv 1808.01400 ↗First posted 4 Aug 2018cs.LG cs.PL stat.MLcited by 179

Not on the map. Why?

Abstract (arXiv)

The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval. Sequence-to-sequence (seq2seq) models, adopted from neural machine translation (NMT), have achieved state-of-the-art performance on these tasks by treating source code as a sequence of tokens. We present rm scriptsize CODE2SEQ: an alternative approach that leverages the syntactic structure of programming languages to better encode source code. Our model represents a code snippet as the set of compositional paths in its abstract syntax tree (AST) and uses attention to select the relevant paths while decoding. We demonstrate the effectiveness of our approach for two tasks, two programming languages, and four datasets of up to 16M examples. Our model significantly outperforms previous models that were specifically designed for programming languages, as well as state-of-the-art NMT models. An interactive online demo of our model is available at http://code2seq.org. Our code, data and trained models are available at http://github.com/tech-srl/code2seq.

Key facts. Cited by 179 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 54; 2022: 38; 2023: 38; 2024: 21; 2025: 22; 2026: 5.

179 papers.

Sort:

By area:

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  3. 2021Unified Pre-training for Program Understanding and Generationcited by 366
  4. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 300
  5. 2021TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generationcited by 120
  6. 2023CodeBERTScore: Evaluating Code Generation with Pretrained Models of Codecited by 102
  7. 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 89
  8. 2021CURE: Code-Aware Neural Machine Translation for Automatic Program Repaircited by 86
  9. 2023Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)cited by 72
  10. 2021DOBF: A Deobfuscation Pre-Training Objective for Programming Languagescited by 68
  11. 2021Language-Agnostic Representation Learning of Source Code from Structure and Contextcited by 63
  12. 2022What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Codecited by 50
38 more
  1. 2023Stealthy Backdoor Attack for Code Modelscited by 49
  2. 2021On the Evaluation of Neural Code Summarizationcited by 48
  3. 2021Multilingual training for Software Engineeringcited by 43
  4. 2021TreeBERT: A Tree-Based Pre-Trained Model for Programming Languagecited by 41
  5. 2022Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Codecited by 39
  6. 2024Securing Large Language Models: Threats, Vulnerabilities and Responsible Practicescited by 37
  7. 2021Neural Transfer Learning for Repairing Security Vulnerabilities in C Codecited by 36
  8. 2021What do pre-trained code models know about code?cited by 36
  9. 2023Automatic Code Summarization via ChatGPT: How Far Are We?cited by 34
  10. 2023Distilled GPT for Source Code Summarizationcited by 31
  11. 2021Code Completion by Modeling Flattened Abstract Syntax Trees as Graphscited by 30
  12. 2021Code Structure Guided Transformer for Source Code Summarizationcited by 30
  13. 2021CodeQA: A Question Answering Dataset for Source Code Comprehensioncited by 30
  14. 2021How could Neural Networks understand Programs?cited by 26
  15. 2021Project-Level Encoding for Neural Source Code Summarization of Subroutinescited by 24
  16. 2021A Survey on Machine Learning Techniques for Source Code Analysiscited by 24
  17. 2024CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Codecited by 24
  18. 2022Transformers over Directed Acyclic Graphscited by 23
  19. 2021Generating Adversarial Computer Programs using Optimized Obfuscationscited by 22
  20. 2021Understanding Neural Code Intelligence Through Program Simplificationcited by 22
  21. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  22. 2021On the Evaluation of Commit Message Generation Models: An Experimental Studycited by 20
  23. 2021Improving Code Summarization with Block-wise Abstract Syntax Tree Splittingcited by 19
  24. 2021Memorization and Generalization in Neural Code Intelligence Modelscited by 19
  25. 2023Backdooring Neural Code Searchcited by 19
  26. 2022An Extractive-and-Abstractive Framework for Source Code Summarizationcited by 18
  27. 2025cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Treecited by 17
  28. 2021Shellcode_IA32: A Dataset for Automatic Shellcode Generationcited by 16
  29. 2024Stable Code Technical Reportcited by 16
  30. 2021GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Searchcited by 15
  31. 2023CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programscited by 15
  32. 2021Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchycited by 14
  33. 2022Source Code Summarization with Structural Relative Position Guided Transformercited by 14
  34. 2022M2TS: Multi-Scale Multi-Modal Approach Based on Transformer for Source Code Summarizationcited by 14
  35. 2023A systematic literature review on source code similarity measurement and clone detection: techniques, applications, and challengescited by 14
  36. 2022Cross-Language Binary-Source Code Matching with Intermediate Representationscited by 13
  37. 2022A Survey on Pretrained Language Models for Neural Code Intelligencecited by 13
  38. 2022An Exploratory Study on Code Attention in BERTcited by 12

50 most cited of 179 All 179 (JSON)