The conversion of textual software requirements into UML class diagrams is a critical step in the development and design process in the field of software engineering. This study provides a novel technique for automatically transforming textual software requirements into UML class diagrams using a model-driven engineering methodology. The main goal is to automate converting textual requirements into a visual representation that can be easily understood and implemented, which will speed up the software development process. In our methodology, we employ a combination of rule-based techniques and Naïve Bayes for named entity recognition. This process assists in resolving ambiguity that arises when predefined rules are unable to determine the type of UML element. This makes it possible for us to precisely distinguish the different parts of a class diagram. Using software requirements and the related UML class diagrams, a wide range of experiments were carried out to assess the efficiency of the suggested methodology. The results demonstrate the superiority of the proposed method, achieving an impressive recall metric of 89.44% and a precision metric of 83.72%. These metrics indicate the high accuracy and reliability of the method in capturing the essential elements of the textual requirements and translating them into UML class diagrams.