Label Parsing Technique
This technique automatically annotates process model activities with their semantic components, such as action and business object. Details about this technique are available here.
Download Python Source Code
Download Data Set
Natural Language Generation Technique
This technique generates natural-looking texts from BPMN process models. It can work with process models of arbitrary structure, makes minimal assumptions on the grammar of the comprised element labels, and preserves control flow order in the text. Details about the technique can be found here. Please note that a valid license for the RealPro Realizer must be added to the file “Realpro.properties”. However, the license can be freely obtained for academic purposes.
Process Model Matching
Below find the process model matching data sets I have used in my work. You are free to use them for your research as long as you refer to the respective Process Model Matching Contest papers in your work.
University Admission Data Set
This set contains process models representing the admission processes of nine German universities. All models contain English text only. The models have been created by different modelers using varying terminology and capturing activities at different levels of granularity.
Download Petri Net Version (Process Model Matching Contest 2013)
Download BPMN Version (Process Model Matching Contest 2015)
Birth Registration Data Set
This set contains nine models of birth registration processes from Germany, Russia, South Africa, and the Netherlands. Four models were created by graduate students at the HU Berlin and five of the models stem from a process analysis in Dutch municipalities. All models contain English text and are available as Petri-nets in the PNML format.
Download Petri Net Version (Process Model Matching Contest 2013 and 2015)