HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks

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.

References in corpus (6)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
• Improved Automatic Summarization of Subroutines via Attention to File Context
• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
• How Much Automation Does a Data Scientist Want?
• How do Data Science Workers Collaborate? Roles, Workflows, and Tools

Cited by in corpus (2)

• Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities
• Documentation Matters: Human-Centered AI System to Assist Data Science Code Documentation in Computational Notebooks