Automatic Code Documentation Generation Using GPT-3

Autor:	Khan, Junaed Younus, Uddin, Gias
Rok vydání:	2022
Předmět:	Computer Science - Software Engineering
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted in IEEE/ACM International Conference on Automated Software Engineering (ASE 2022) - NIER
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2209.02235 Zobrazit plný text záznamu View this record from Arxiv