论文标题
使用GPT-3生成自动代码文档
Automatic Code Documentation Generation Using GPT-3
论文作者
论文摘要
源代码文档是有效软件开发的重要工件。代码文档可能会从自动化中受益匪浅，因为手动文档通常是在劳动，资源和时间密集型。在本文中，我们使用Codex来创建自动代码文档。 Codex是一种基于GPT-3的模型，对天然和编程语言进行了预培训。我们发现，即使使用一声学习（即，仅提供一个训练示例），Codex也优于现有技术。对于六种不同的编程语言，Codex的总体BLEU得分为20.6（比早期最新技术提高了11.2％）。因此，Codex显示了自动代码文档生成以支持各种开发任务的未来有望和保证。
Source code documentation is an important artifact for efficient software development. Code documentation could greatly benefit from automation since manual documentation is often labouring, resource and time-intensive. In this paper, we employed Codex for automatic code documentation creation. Codex is a GPT-3 based model pre-trained on both natural and programming languages. We find that Codex outperforms existing techniques even with basic settings like one-shot learning (i.e., providing only one example for training). Codex achieves an overall BLEU score of 20.6 for six different programming languages (11.2% improvement over earlier state-of-the-art techniques). Thus, Codex shows promise and warrants in-depth future studies for automatic code documentation generation to support diverse development tasks.
