Automated Glossary Extraction from Collaborative Requirements Models

A glossary presents the terms of the common vocabulary of a project. Even though documentation in natural language is the primary source for these terms, requirements models are also valuable resources as they capture requirements and domain knowledge. Yet, models are often neglected when extracting glossary terms. This paper proposes a method to automatically extract a glossary from a set of models by applying natural language processing techniques. The output of our method is a list and a graph of glossary terms where related terms are connected based on their relatedness.