Automated generation of terminological dictionary from textual business rules

Abstract

To support decision making, organizations tend to operate according to Business Rules, which are usually represented in a natural language format easily understood by all intervenors. According to the business rules manifesto by the Business Rules Group (OMG), rules build on facts, and facts build on concepts as expressed by terms. To avoid ambiguity and misunderstanding, the standardization of the terminology used at the business level becomes a persistent need. However, doing so manually is error prone and time consuming, especially that the Business Rules are the subject of continuous updating. In this paper, we present an automated approach to generate the Business Vocabulary from textual statements of Business Rules. Our approach is distinguished from existing works in that it extracts the Terminological Dictionary as described by the Semantic of Business Vocabulary and Rules (SBVR) standard to provide a more comprehensive meaning for each concept. Accordingly, an in‐depth Natural Language Processing (NLP) is used to extract not only flat list of terms and relations, but also extra specifications and implicit knowledge. With a satisfactory result, our approach has proved its capability to automatically generate the SBVR Terminological Dictionary from large number of natural language business rules statements.