HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks
Xuye Liu, Dakuo Wang, April Wang, Yufang Hou, Lingfei Wu
Abstract
Jupyter notebook allows data scientists to write machine learning code together with its documentation in cells. In this paper, we propose a new task of code documentation generation (CDG) for computational notebooks. In contrast to the previous CDG tasks which focus on generating documentation for single code snippets, in a computational notebook, one documentation in a markdown cell often corresponds to multiple code cells, and these code cells have an inherent structure. We proposed a new model (HAConvGNN) that uses a hierarchical attention mechanism to consider the relevant code cells and the relevant code tokens information when generating the documentation. Tested on a new corpus constructed from well-documented Kaggle notebooks, we show that our model outperforms other baseline models.
BibTeX
@inproceedings{liu-etal-2021-haconvgnn-hierarchical,
title = "{HAC}onv{GNN}: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in {J}upyter Notebooks",
author = "Liu, Xuye and
Wang, Dakuo and
Wang, April and
Hou, Yufang and
Wu, Lingfei",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.381/",
doi = "10.18653/v1/2021.findings-emnlp.381",
pages = "4473--4485"
}