Data-driven Annotation of Textual Process Descriptions based on Formal Meaning Representations

Business process models are an established means for bridging the gap between domain experts and rather technically oriented software specialists. Furthermore, they facilitate system-aided analysis and execution of business processes. However, it requires a significant effort to learn a formal process modeling language like BPMN. Among others, this is one reason why companies often stick to informal textual process descriptions. However, in contrast to formal models, natural language text usually cannot be automatically processed by algorithms. Approaches for transforming natural language texts into process models have been investigated for several years and show promising results but also clarify the complexity of this task. Thus, recent research also focuses on annotated textual process descriptions. While still human-readable, they additionally contain annotations following a formal scheme. Thus, they also enable automated processing by, for instance, formal reasoning and simulation. State-of-the-art techniques for automatically annotating textual process descriptions are either based on hand-crafted rule sets or artificial neural networks. Maintaining complex rule sets requires a significant manual effort and the approaches using neural networks suffer from rather low result quality. In this paper we present an approach based on Semantic Parsing and Graph Convolutional Networks that avoids manually defined rules and provides significantly better results than existing techniques based on neural networks. A comprehensive evaluation using multiple data sets from both academia and industry shows encouraging results and differentiates between several applied text features.

03: NLP and Text Main Track