Business process models are used to identify control-flow relationships of tasks extracted from information system event logs. These event logs may fail to capture critical tasks executed outside of regular logging environments, but such latent tasks may be inferred from unstructured natural language texts. This paper highlights two workflow discovery pipeline components which use NLP and sequence mining techniques to extract workflow candidates from such texts. We present our Event Labeling and Sequence Analysis (ELSA) prototype which implements these components, associated approach methodologies, and performance results of our algorithm against ground truth data from the Apache Software Foundation Public Email Archive.
CITATION STYLE
Shing, L., Wollaber, A., Chikkagoudar, S., Yuen, J., Alvino, P., Chambers, A., & Allard, T. (2019). Extracting Workflows from Natural Language Documents: A First Step. In Lecture Notes in Business Information Processing (Vol. 342, pp. 294–300). Springer Verlag. https://doi.org/10.1007/978-3-030-11641-5_23
Mendeley helps you to discover research relevant for your work.