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

arXiv: https://arxiv.org/abs/2104.01002 · HTML: https://mlsanity.com/paper/2104.01002/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 31 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [code2seq: Generating Sequences from Structured Representations of Code](https://mlsanity.com/paper/1808.01400/) (2018)
- [A Convolutional Attention Network for Extreme Summarization of Source Code](https://mlsanity.com/paper/1602.03001/) (2016)
- [Improved Code Summarization via a Graph Neural Network](https://mlsanity.com/paper/2004.02843/) (2020)
- [How do Data Science Workers Collaborate? Roles, Workflows, and Tools](https://mlsanity.com/paper/2001.06684/) (2020)
- [Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation](https://mlsanity.com/paper/1908.04942/) (2019)
- [JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation](https://mlsanity.com/paper/1910.02216/) (2019)
- [Recommendations for Datasets for Source Code Summarization](https://mlsanity.com/paper/1904.02660/) (2019)
- [Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks](https://mlsanity.com/paper/1804.00823/) (2018)
- [Improved Automatic Summarization of Subroutines via Attention to File Context](https://mlsanity.com/paper/2004.04881/) (2020)
- [How Much Automation Does a Data Scientist Want?](https://mlsanity.com/paper/2101.03970/) (2021)
- [Action Word Prediction for Neural Source Code Summarization](https://mlsanity.com/paper/2101.02742/) (2021)

## Built on by (most cited first, 6 of 6)

- [Execution-based Evaluation for Data Science Code Generation Models](https://mlsanity.com/paper/2211.09374/) (2022)
- [Python Code Generation by Asking Clarification Questions](https://mlsanity.com/paper/2212.09885/) (2022)
- [Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work](https://mlsanity.com/paper/2203.11085/) (2022)
- [A Survey of Deep Learning Models for Structural Code Understanding](https://mlsanity.com/paper/2205.01293/) (2022)
- [Do Current Language Models Support Code Intelligence for R Programming Language?](https://mlsanity.com/paper/2410.07793/) (2024)
- [Predicting the Understandability of Computational Notebooks through Code Metrics Analysis](https://mlsanity.com/paper/2406.10989/) (2024)

## Abstract (arXiv)

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.