csebuetnlp / CoDescLinks
A large dataset of 4.2m Java source code and parallel data of their description from code search, and code summarization studies.
☆54Updated 3 years ago
Alternatives and similar repositories for CoDesc
Users that are interested in CoDesc are comparing it to the libraries listed below
Sorting:
- Official code of our work, AVATAR: A Parallel Corpus for Java-Python Program Translation.☆58Updated last year
- Code for the paper "A Structural Model for Contextual Code Changes"☆32Updated 2 years ago
- Releasing code for "ReCode: Robustness Evaluation of Code Generation Models"☆52Updated last year
- Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].☆187Updated 3 years ago
- A collection of recent papers, benchmarks and datasets of AI4Code domain.☆58Updated last year
- ☆45Updated 4 months ago
- CoditT5: Pretraining for Source Code and Natural Language Editing☆28Updated 9 months ago
- This repo is the benchmark for source code summarization on C language☆26Updated 4 years ago
- Source Code for ACL-21 main conference paper "CoSQA: 20,000+ Web Queries for Code Search and Question Answering".☆46Updated 2 years ago
- VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning☆40Updated 2 years ago
- Models and datasets for annotated code search.☆35Updated 2 years ago
- [ICML 2021] Break-It-Fix-It: Unsupervised Learning for Program Repair☆119Updated 2 years ago
- [EACL 2024] ICE-Score: Instructing Large Language Models to Evaluate Code☆79Updated last year
- Learning to Update Natural Language Comments Based on Code Changes: Artifact☆33Updated 5 years ago
- Contains the code and data for our #ICSE2022 paper titled as "CodeFill: Multi-token Code Completion by Jointly Learning from Structure an…☆15Updated 3 years ago
- Code and data for ACL20 paper "Incorporating External Knowledge through Pre-training for Natural Language to Code Generation"☆97Updated last month
- A Tree-Based Transformer Architecture for Code Generation. (AAAI'20)☆91Updated 3 years ago
- Recent Advances in Programming Language Pre-Trained Models (PL-PTMs)☆59Updated 3 years ago
- Code for generating the JuICe dataset.☆37Updated 4 years ago
- Code and data for AAAI 2022 paper "Multilingual Code Snippets Training for Program Translation"☆10Updated 3 years ago
- Code implementation for CoTexT: Multi-task Learning with Code-Text Transformer☆36Updated 4 years ago
- Re-implementation of "CODE2SEQ: GENERATING SEQUENCES FROM STRUCTURED REPRESENTATIONS OF CODE"☆45Updated last year
- CodeBERTScore: an automatic metric for code generation, based on BERTScore☆202Updated last year
- Contrastive Code Representation Learning: functionality-based JavaScript embeddings through self-supervised learning☆168Updated 3 years ago
- Mapping Language to Code in a Programmatic Context☆80Updated 4 years ago
- Improving Machine Translation Systems via Isotopic Replacement☆12Updated 2 years ago
- Code for "Learning Structural Edits via Incremental Tree Transformations" (ICLR'21)☆41Updated 4 years ago
- JEMMA: An Extensible Java dataset for Many ML4Code Applications☆19Updated 2 years ago
- Empirical Study of Transformers for Source Code & A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Sourc…☆65Updated 3 years ago
- A Pre-trained BERT on StackOverflow Corpus☆47Updated 4 years ago