Can Code Metrics Enhance Documentation Generation for Computational Notebooks?
Abstract
In software development, code documentation is crucial for collaboration and maintenance, especially as projects become more complex. However, it is often neglected due to the tedious effort it requires. This paper explores automating documentation generation for computational notebooks, focusing on the impact of code metrics such as lines of code, API popularity, and complexity on this task. Using a dataset of 22K code-documentation pairs, we compare deep learning models with and without code metric augmentation. The results show that incorporating these metrics significantly improves the accuracy of documentation generation, underscoring the connection between code metrics and quality documentation.
BibTeX
@inproceedings{Ghahfarokhi-al:ASE24,
author = {Mojtaba Mostafavi Ghahfarokhi and
Hamed Jahantigh and
Sepehr Kianiangolafshani and
Ashkan Khademian and
Alireza Asadi and
Abbas Heydarnoori},
title = {Can Code Metrics Enhance Documentation Generation for Computational Notebooks?},
booktitle = {ASE},
pages = {2472--2473},
publisher = {{ACM}},
year = {2024},
}