awesome-programming-language-pretraining-papers
Recent Advances in Programming Language Pre-Trained Models (PL-PTMs)
https://github.com/yuewang-cuhk/awesome-programming-language-pretraining-papers
Last synced: 3 days ago
JSON representation
-
General PL-PTMs
- PYMT5: multi-mode translation of natural language and PYTHON code with transformers
- Learning and Evaluating Contextual Embedding of Source Code - research/google-research/tree/master/cubert)\] ICML 2020 (CuBERT)
- CodeBERT:A Pre-Trained Model for Programming and Natural Languages
- GraphCodeBERT: Pre-training Code Representations with Data Flow
- Unified Pre-training for Program Understanding and Generation
- Unsupervised Translation of Programming Languages
- Exploring Software Naturalness through Neural Language Models - BERT)
- Contrastive Code Representation Learning
- DOBF: A Deobfuscation Pre-Training Objective for Programming Languages
- Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks - mastropaolo/T5-learning-ICSE_2021)\] ICSE 2021
- How could Neural Networks understand Programs?
- CoTexT: Multi-task Learning with Code-Text Transformer
- Disentangled Code Representation Learning for Multiple Programming Languages - Fingings 2021 (CODEDISEN)
- SYNCOBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
- TreeBERT: A Tree-Based Pre-Trained Model for Programming Language
- CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation - codet5-system-can-understand-and-generate-code/)\]\[[slide](https://yuewang-cuhk.github.io/file/CodeT5_final_slide_p20.pdf)\]\[[poster](https://yuewang-cuhk.github.io/file/CodeT5_Poster.pdf)\]
- How could Neural Networks understand Programs?
- SYNCOBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
- CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation - codet5-system-can-understand-and-generate-code/)\]\[[slide](https://yuewang-cuhk.github.io/file/CodeT5_final_slide_p20.pdf)\]\[[poster](https://yuewang-cuhk.github.io/file/CodeT5_Poster.pdf)\]
- CodeTrans: Towards Cracking the Language of Silicone’s Code Through Self-Supervised Deep Learning and High Performance Computing
-
Task-specific PL-PTMs
- Multi-task Learning based Pre-trained Language Model for Code Completion
- IntelliCode Compose: Code Generation using Transformer
- Improving Code Autocompletion with Transfer Learning
- Generating Bug-Fixes Using Pretrained Transformers
- DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons
- TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer
- CURE: Code-Aware Neural Machine Translation for Automatic Program Repair
- Unit Test Case Generation with Transformers and Focal Context
- Evaluating Large Language Models Trained on Code
- Program Synthesis with Large Language Models
- DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons
- Unit Test Case Generation with Transformers and Focal Context
-
Other Deep Models for Code-related Tasks
- Language-Agnostic Representation Learning of Source Code from Structure and Context - transformer)\] ICLR 2021 (Code Transformer)
- GN-Transformer: Fusing AST and Source Code information in Graph Networks - Transformer)
- HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMS
-
Benchmarks & Datasets
Categories
Sub Categories