Declarative Process Discovery: Linking Process and Textual Views
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Fulltext
Indsendt manuskript, 462 KB, PDF-dokument
Business Process models are conceptual representations of work practices. However, a process is more than its model: key information about the rationale of the process is hidden in accompanying documents. We present a framework for business process discovery from process descriptions in texts. We use declarative process models as our target modelling technique. The manual discovery of declarative process models from texts is particularly hard as users have difficulties identifying textual fragments denoting business rules. Our framework combines machine-learning and expert system techniques in order to provide an algorithmic solution to discovery. The combination of the two techniques allows 1) the identification of process components in texts, 2) the enrichment of predictions with semantic information, and 3) the generation of consolidated hybrid models that link text fragments and process elements. Our initial evaluation reports state-of-the-art performance in accuracy against user annotated models, and it has been implemented and adopted by our industrial partner.
Originalsprog | Engelsk |
---|---|
Titel | Intelligent Information Systems : CAiSE Forum 2021 Melbourne, VIC, Australia, June 28 – July 2, 2021 Proceedings |
Forlag | Springer |
Publikationsdato | 2021 |
Sider | 109-117 |
ISBN (Trykt) | 978-3-030-79107-0 |
ISBN (Elektronisk) | 978-3-030-79108-7 |
DOI | |
Status | Udgivet - 2021 |
Begivenhed | International Conference on Advanced Information Systems Engineering - Varighed: 28 jun. 2021 → 2 jul. 2021 Konferencens nummer: 33 https://caise21.org/ |
Konference
Konference | International Conference on Advanced Information Systems Engineering |
---|---|
Nummer | 33 |
Periode | 28/06/2021 → 02/07/2021 |
Internetadresse |
Navn | Lecture Notes in Business Information Processing |
---|---|
Vol/bind | 424 |
ISSN | 1865-1348 |
- Det Natur- og Biovidenskabelige Fakultet
Forskningsområder
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 273366034