# Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications

arXiv: https://arxiv.org/abs/2210.14441 · HTML: https://mlsanity.com/paper/2210.14441/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2022.

## Built on by (most cited first, 3 of 3)

- [NOMAD: A Multi-Agent LLM System for UML Class Diagram Generation from Natural Language Requirements](https://mlsanity.com/paper/2511.22409/) (2025)
- [Modeling and Recovering Hierarchical Structural Architectures of ROS 2 Systems from Code and Launch Configurations using LLM-based Agents](https://mlsanity.com/paper/2602.18644/) (2026)
- [Code2UML: Agentic LLMs with context engineering for scalable software visualization](https://mlsanity.com/paper/2605.24453/) (2026)

## Abstract (arXiv)

In model-driven engineering (MDE), UML class diagrams serve as a way to plan and communicate between developers. However, it is complex and resource-consuming. We propose an automated approach for the extraction of UML class diagrams from natural language software specifications. To develop our approach, we create a dataset of UML class diagrams and their English specifications with the help of volunteers. Our approach is a pipeline of steps consisting of the segmentation of the input into sentences, the classification of the sentences, the generation of UML class diagram fragments from sentences, and the composition of these fragments into one UML class diagram. We develop a quantitative testing framework specific to UML class diagram extraction. Our approach yields low precision and recall but serves as a benchmark for future research.