Authors: George Baryannis, Mussa Omar
Tags: 2020, conceptual modeling
The process of converting natural language specifications into conceptual models requiresdetailed analysis of natural language text, and designers frequently make mistakes whenundertaking this transformation manually. Although many approaches have been used topartly automate this process, one of the main limitations is the lack of a domain-independentontology that can be used as a repository for entities and relationships, thus guiding thetransformation process. In this paper, a semi-automated system for mapping natural languagetext into conceptual models is proposed. The system, called SACMES, combines a linguisticapproach with an ontological approach and human intervention to achieve the task. SACMESlearns from the natural language specifications that it processes and stores the information thatis learnt in a conceptual model ontology and a user history knowledge database. It then usesthe stored information to improve performance and reduce the need for human intervention.The evaluation conducted on SACMES demonstrates that: (1) by using the system, precisionand recall for users identifying entities of conceptual models is increased by 6% and 13%,respectively, while for relationships, increases are even higher, 14% for precision and 23% forrecall; (2) the performance of the system is improved by processing more natural languagerequirements, and thus, the need for human intervention is decreased.Read the full paper here: https://reader.elsevier.com/reader/sd/pii/S0169023X19301429?token=4F5C7C0E5FFA003F0E5038C7CD4C4DC5D4455E9AEED4862CC84222F27D7C5739A35E9E98A6D70B1AFD27882BCA87B463
