delihiros / pseudogen
A tool to automatically generate pseudo-code from source code.
☆163Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for pseudogen
- Summarizing Source Code using a Neural Attention Model - CODENN☆236Updated last year
- MLonCode community effort to implement Learning Distributed Representations of Code (https://arxiv.org/pdf/1803.09473.pdf)☆40Updated 6 years ago
- Tree-based Autofolding Software Summarization Algorithm☆42Updated 8 years ago
- Probabilistic API Mining☆53Updated 6 years ago
- evaluation dataset consisting of natural language query and code snippet pairs☆123Updated 6 months ago
- Preprocessed Python functions and docstrings for automated code documentation (code2doc) and automated code generation (doc2code) tasks.☆201Updated 4 years ago
- [ICML 2020] DrRepair: Learning to Repair Programs from Error Messages☆191Updated 3 years ago
- Learning to Auto-Complete using RNN Language Models☆156Updated 7 years ago
- Program Synthesis☆144Updated 3 years ago
- Repository for the code of the "A Convolutional Attention Network for Extreme Summarization of Source Code" paper☆120Updated 8 years ago
- Collected solutions from Google Code Jam programming competition (2008-2020).☆61Updated 2 months ago
- Deepcoder paper implementation☆113Updated last year
- Artifacts and other data for "Code Vectors: Understanding Programs Through Embedded Abstraced Symbolic Traces"☆22Updated 4 years ago
- 58069 Java source code diffs. http://arxiv.org/pdf/1807.03200☆91Updated 5 years ago
- Utilities used in the experiments for the DeepCoder paper (ICLR'17)☆59Updated last year
- an implementation of "code2vec: Learning Distributed Representations of Code"☆29Updated 4 months ago
- Sequence-to-Sequence Learning for End-to-End Program Repair (IEEE TSE 2019). Open-science repo. http://arxiv.org/pdf/1901.01808☆81Updated last year
- Contains the code for our ICSE 2020 paper: Big Code != Big Vocabulary: Open-Vocabulary Language Models for Source Code and for its earlie…☆83Updated last year
- Characterizing the natural language descriptions in software logging statements [ASE'18]☆17Updated 5 years ago
- Convert source code into numerical tokens☆64Updated last year
- ☆16Updated 4 months ago
- Baseline for the Conala: Code/Natural Language Challenge☆61Updated 3 years ago
- Paper Artifacts for "Aroma: Code Recommendation via Structural Code Search"☆57Updated 3 years ago
- Source code understanding via Machine Learning techniques☆134Updated last year
- Code for the model presented in the paper: "code2seq: Generating Sequences from Structured Representations of Code"☆556Updated 3 months ago
- ☆50Updated 4 years ago
- Sourcerer's Code Clone project☆206Updated 2 years ago
- Machine learning models for MLonCode trained using the source{d} stack☆19Updated 5 years ago
- A PyTorch implementation of `code2vec: Learning Distributed Representations of Code` (Alon et al., 2018)☆35Updated 5 years ago
- Demonstration of the path-extraction process shown in the paper "A General Path-Based Representation for Predicting Program Properties"☆24Updated 3 years ago