# DocGen: Generating Detailed Parameter Docstrings in Python

arXiv: https://arxiv.org/abs/2311.06453 · HTML: https://mlsanity.com/paper/2311.06453/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 63 references that are in the map.
- First posted on arXiv 11 Nov 2023.

## Builds on (most cited first, 22 of 22)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [code2seq: Generating Sequences from Structured Representations of Code](https://mlsanity.com/paper/1808.01400/) (2018)
- [PyMT5: multi-mode translation of natural language and Python code with transformers](https://mlsanity.com/paper/2010.03150/) (2020)
- [A Neural Model for Generating Natural Language Summaries of Program Subroutines](https://mlsanity.com/paper/1902.01954/) (2019)
- [CoTexT: Multi-task Learning with Code-Text Transformer](https://mlsanity.com/paper/2105.08645/) (2021)
- [A parallel corpus of Python functions and documentation strings for automated code documentation and code generation](https://mlsanity.com/paper/1707.02275/) (2017)
- [SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations](https://mlsanity.com/paper/2201.01549/) (2022)
- [TypeWriter: Neural Type Prediction with Search-based Validation](https://mlsanity.com/paper/1912.03768/) (2019)
- [ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation](https://mlsanity.com/paper/2104.08006/) (2021)
- [An Empirical Comparison of Pre-Trained Models of Source Code](https://mlsanity.com/paper/2302.04026/) (2023)
- [Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code](https://mlsanity.com/paper/2205.11739/) (2022)
- [Type4Py: Practical Deep Similarity Learning-Based Type Inference for Python](https://mlsanity.com/paper/2101.04470/) (2021)
- [Static Inference Meets Deep Learning: A Hybrid Type Inference Approach for Python](https://mlsanity.com/paper/2105.03595/) (2021)
- [A Large-Scale Comparison of Python Code in Jupyter Notebooks and Scripts](https://mlsanity.com/paper/2203.16718/) (2022)
- [What Do Developers Discuss about Code Comments?](https://mlsanity.com/paper/2108.07648/) (2021)
- [Do Comments follow Commenting Conventions? A Case Study in Java and Python](https://mlsanity.com/paper/2108.10766/) (2021)

## Abstract (arXiv)

Documentation debt hinders the effective utilization of open-source software. Although code summarization tools have been helpful for developers, most would prefer a detailed account of each parameter in a function rather than a high-level summary. However, generating such a summary is too intricate for a single generative model to produce reliably due to the lack of high-quality training data. Thus, we propose a multi-step approach that combines multiple task-specific models, each adept at producing a specific section of a docstring. The combination of these models ensures the inclusion of each section in the final docstring. We compared the results from our approach with existing generative models using both automatic metrics and a human-centred evaluation with 17 participating developers, which proves the superiority of our approach over existing methods.