@inproceedings{FreyerThewesMeinecke2023,
  author    = {Freyer, Nils and Thewes, Dustin and Meinecke, Matthias},
  title     = {GUIDO: a hybrid approach to guideline discovery \& ordering from natural language texts},
  series = {Proceedings of the 12th International Conference on Data Science, Technology and Applications DATA - Volume 1},
  booktitle = {Proceedings of the 12th International Conference on Data Science, Technology and Applications DATA - Volume 1},
  editor    = {Gusikhin, Oleg and Hammoudi, Slimane and Cuzzocrea, Alfredo},
  isbn      = {978-989-758-664-4},
  issn      = {2184-285X},
  doi       = {10.5220/0012084400003541},
  pages     = {335 -- 342},
  year      = {2023},
  abstract  = {Extracting workflow nets from textual descriptions can be used to simplify guidelines or formalize textual descriptions of formal processes like business processes and algorithms. The task of manually extracting processes, however, requires domain expertise and effort. While automatic process model extraction is desirable, annotating texts with formalized process models is expensive. Therefore, there are only a few machine-learning-based extraction approaches. Rule-based approaches, in turn, require domain specificity to work well and can rarely distinguish relevant and irrelevant information in textual descriptions. In this paper, we present GUIDO, a hybrid approach to the process model extraction task that first, classifies sentences regarding their relevance to the process model, using a BERT-based sentence classifier, and second, extracts a process model from the sentences classified as relevant, using dependency parsing. The presented approach achieves significantly better resul ts than a pure rule-based approach. GUIDO achieves an average behavioral similarity score of 0.93. Still, in comparison to purely machine-learning-based approaches, the annotation costs stay low.},
  language  = {en}
}