# Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications Source: [Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications]() Collection index: [llms.txt]() Data updated: 2026-01-01T15:32:54.967Z Authors: Song Yang, Houari Sahraoui Published: 2022-10-26T03:24:46.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Class Generation on English specifications dataset](): Class generation; English specifications dataset; Precision: 0.355. - [UML Relationship Generation on English specifications dataset Full (test)](): UML Relationship Generation; English specifications dataset Full (test); Connectivity Similarity: 63.9. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()