NaturalCC: A Toolkit to Naturalize the Source Code Corpus

TL;DR

NaturalCC is a versatile toolkit designed to facilitate research in big code analysis by providing efficient, extensible, and user-friendly tools for natural language and programming language tasks, supporting reproducibility and implementation of state-of-the-art models.

Contribution

It introduces an extensible toolkit built on Fairseq and PyTorch that simplifies reproducing and developing big code analysis models with multi-GPU support and user interfaces.

Findings

Supports multiple big code analysis tasks like code completion and comment generation

Enables fast training with multi-GPU and mixed-precision processing

Includes state-of-the-art baseline models for various tasks

Abstract

We present NaturalCC, an efficient and extensible toolkit to bridge the gap between natural language and programming language, and facilitate the research on big code analysis. Using NaturalCC, researchers both from natural language or programming language communities can quickly and easily reproduce the state-of-the-art baselines and implement their approach. NaturalCC is built upon Fairseq and PyTorch, providing (1) an efficient computation with multi-GPU and mixed-precision data processing for fast model training, (2) a modular and extensible framework that makes it easy to reproduce or implement an approach for big code analysis, and (3) a command line interface and a graphical user interface to demonstrate each model's performance. Currently, we have included several state-of-the-art baselines across different tasks (e.g., code completion, code comment generation, and code retrieval) for demonstration. The video of this demo is available at https://www.youtube.com/watch?v=q4W5VSI-u3E&t=25s.