@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}
}
@inproceedings{KohlFreyerKraemeretal.2023,
  author    = {Kohl, Philipp and Freyer, Nils and Kr{\"a}mer, Yoka and Werth, Henri and Wolf, Steffen and Kraft, Bodo and Meinecke, Matthias and Z{\"u}ndorf, Albert},
  title     = {ALE: a simulation-based active learning evaluation framework for the parameter-driven comparison of query strategies for NLP},
  series = {Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science},
  booktitle = {Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science},
  editor    = {Conte, Donatello and Fred, Ana and Gusikhin, Oleg and Sansone, Carlo},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-031-39058-6 (Print)},
  doi       = {978-3-031-39059-3},
  pages     = {235 -- 253},
  year      = {2023},
  abstract  = {Supervised machine learning and deep learning require a large amount of labeled data, which data scientists obtain in a manual, and time-consuming annotation process. To mitigate this challenge, Active Learning (AL) proposes promising data points to annotators they annotate next instead of a subsequent or random sample. This method is supposed to save annotation effort while maintaining model performance. However, practitioners face many AL strategies for different tasks and need an empirical basis to choose between them. Surveys categorize AL strategies into taxonomies without performance indications. Presentations of novel AL strategies compare the performance to a small subset of strategies. Our contribution addresses the empirical basis by introducing a reproducible active learning evaluation (ALE) framework for the comparative evaluation of AL strategies in NLP. The framework allows the implementation of AL strategies with low effort and a fair data-driven comparison through defining and tracking experiment parameters (e.g., initial dataset size, number of data points per query step, and the budget). ALE helps practitioners to make more informed decisions, and researchers can focus on developing new, effective AL strategies and deriving best practices for specific use cases. With best practices, practitioners can lower their annotation costs. We present a case study to illustrate how to use the framework.},
  language  = {en}
}