code-gen/cscg
Code Generation as a Dual Task of Code Summarization.
This tool helps AI/ML researchers explore a novel approach to code generation and summarization. It takes in structured code and its corresponding natural language annotations, then processes them to build language models. The output is a set of trained language models and computed probabilities for both code and annotations, useful for advancing research in AI for software engineering.
No commits in the last 6 months.
Use this if you are an AI/ML researcher or practitioner studying the relationship between code and its natural language descriptions, particularly for tasks like code generation or summarization.
Not ideal if you are looking for an out-of-the-box solution to generate code or summaries for your daily development work, as this is a research-oriented implementation.
Stars
30
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 28, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/code-gen/cscg"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
k4black/codebleu
Pip compatible CodeBLEU metric implementation available for linux/macos/win
LiveCodeBench/LiveCodeBench
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of...
EdinburghNLP/code-docstring-corpus
Preprocessed Python functions and docstrings for automated code documentation (code2doc) and...
hendrycks/apps
APPS: Automated Programming Progress Standard (NeurIPS 2021)
solis-team/Hydra
[FSE 2026] Do Not Treat Code as Natural Language: Implications for Repository-Level Code...