A Framework for Processing Textual Descriptions of Business Processes using a Constrained Language -- Technical Report
This addresses the challenge for non-experts in business process modeling by providing a more accessible interface, though it appears incremental as it builds on existing constrained language and LLM techniques.
The authors tackled the problem of enabling non-experts to create process models by proposing BeePath, a framework that translates constrained natural language descriptions into formal models like Petri nets and DECLARE, using LLMs to convert unstructured text into this constrained format.
This report explores how (potentially constrained) natural language can be used to enable non-experts to develop process models by simply describing scenarios in plain text. To this end, a framework, called BeePath, is proposed. It allows users to write process descriptions in a constrained pattern-based language, which can then be translated into formal models such as Petri nets and DECLARE. The framework also leverages large language models (LLMs) to help convert unstructured descriptions into this constrained language.