Process Model Generation from Natural Language Text

  • Fabian Friedrich
  • Jan Mendling
  • Frank Puhlmann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6741)


Business process modeling has become an important tool for managing organizational change and for capturing requirements of software. A central problem in this area is the fact that the acquisition of as-is models consumes up to 60% of the time spent on process management projects. This is paradox as there are often extensive documentations available in companies, but not in a ready-to-use format. In this paper, we tackle this problem based on an automatic approach to generate BPMN models from natural language text. We combine existing tools from natural language processing in an innovative way and augmented them with a suitable anaphora resolution mechanism. The evaluation of our technique shows that for a set of 47 text-model pairs from industry and textbooks, we are able to generate on average 77% of the models correctly.


Business Process Natural Language Processing Relative Clause Business Process Management World Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Herbst, J., Karagiannis, D.: An inductive approach to the acquisition and adaptation of workflow models. In: Proceedings of the IJCAI, pp. 52–57 (1999)Google Scholar
  2. 2.
    Frederiks, P., Van der Weide, T.: Information modeling: the process and the required competencies of its participants. Data & Knowledge Engineering 58(1), 4–20 (2006)CrossRefGoogle Scholar
  3. 3.
    Scheer, A.: ARIS-business process modeling. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  4. 4.
    Reijers, H., Limam, S., Van Der Aalst, W.: Product-based workflow design. Journal of Management Information Systems 20(1), 229–262 (2003)CrossRefGoogle Scholar
  5. 5.
    Gruber, T.: Automated knowledge acquisition for strategic knowledge. Machine Learning 4(3), 293–336 (1989)Google Scholar
  6. 6.
    Blumberg, R., Atre, S.: The problem with unstructured data. DM Review 13, 42–49 (2003)Google Scholar
  7. 7.
    White, M.: Information overlook. EContent(26:7) (2003)Google Scholar
  8. 8.
    OMG, eds.: Business Process Model and Notation (BPMN) Version 2.0 (June 2010)Google Scholar
  9. 9.
    Freund, J., Rücker, B., Henninger, T.: Praxishandbuch BPMN. Hanser (2010)Google Scholar
  10. 10.
    Melčuk, I.: Dependency syntax: theory and practice, New York (1988)Google Scholar
  11. 11.
    Marcus, M., Marcinkiewicz, M., Santorini, B.: Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics 19(2), 330 (1993)Google Scholar
  12. 12.
    de Marneffe, M., Manning, C.: The Stanford typed dependencies representation. In: Workshop on Cross-Framework and Cross-Domain Parser Evaluation, pp. 1–8 (2008)Google Scholar
  13. 13.
    Baker, C., Fillmore, C., Lowe, J.: The berkeley framenet project. In: 17th Int. Conf. on Computational Linguistics, pp. 86–90 (1998)Google Scholar
  14. 14.
    Miller, G.A.: Wordnet: A lexical database for english. CACM 38(11), 39–41 (1995)CrossRefGoogle Scholar
  15. 15.
    Achour, C.B.: Guiding scenario authoring. In: 8th European-Japanese Conference on Information Modelling and Knowledge Bases, pp. 152–171. IOS Press, Amsterdam (1998)Google Scholar
  16. 16.
    Li, J., Wang, H., Zhang, Z., Zhao, J.: A policy-based process mining framework: mining business policy texts for discovering process models. ISEB 8(2), 169–188Google Scholar
  17. 17.
    Yue, T., Briand, L., Labiche, Y.: An Automated Approach to Transform Use Cases into Activity Diagrams. Modelling Foundations and Appl., 337–353 (2010)Google Scholar
  18. 18.
    Fliedl, G., Kop, C., Mayr, H., Salbrechter, A., Vöhringer, J., Weber, G., Winkler, C.: Deriving static and dynamic concepts from software requirements using sophisticated tagging. Data & Knowledge Engineering 61(3), 433–448 (2007)CrossRefGoogle Scholar
  19. 19.
    Kop, C., Mayr, H.: Conceptual predesign–bridging the gap between requirements and conceptual design. In: 3rd Int. Conf. on Requirements Eng. p. 90 (1998)Google Scholar
  20. 20.
    Ghose, A., Koliadis, G., Chueng, A.: Process Discovery from Model and Text Artefacts. In: 2007 IEEE Congress on Services, pp. 167–174 (2007)Google Scholar
  21. 21.
    Ghose, A.K., Koliadis, G., Chueng, A.: Rapid business process discovery (R-BPD). In: Parent, C., Schewe, K.-D., Storey, V.C., Thalheim, B. (eds.) ER 2007. LNCS, vol. 4801, pp. 391–406. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  22. 22.
    Sinha, A., Paradkar, A., Kumanan, P., Boguraev, B.: An Analysis Engine for Dependable Elicitation on Natural Language Use Case Description and its Application to Industrial Use Cases. Technical report, IBM (2008)Google Scholar
  23. 23.
    de AR Gonçalves, J.C., Santoro, F.M., Baião, F.A.: A case study on designing processes based on collaborative and mining approaches. In: Int. Conf. on Computer Supported Cooperative Work in Design, Shanghai, China (2010)Google Scholar
  24. 24.
    Fliedl, G., Kop, C., Mayr, H.: From textual scenarios to a conceptual schema. Data & Knowledge Engineering 55(1), 20–37 (2005)CrossRefGoogle Scholar
  25. 25.
    Friedrich, F.: Automated generation of business process models from natural language input. Master’s thesis, Humboldt-Universität zu Berlin (November 2010)Google Scholar
  26. 26.
    Kitzmann, I., Konig, C., Lubke, D., Singer, L.: A Simple Algorithm for Automatic Layout of BPMN Processes. In: IEEE Conf. CEC, pp. 391–398 (2009)Google Scholar
  27. 27.
    Seemann, J.: Extending the sugiyama algorithm for drawing UML class diagrams: Towards automatic layout of object-oriented software diagrams. In: Graph Drawing, pp. 415–424. Springer, Heidelberg (1997)CrossRefGoogle Scholar
  28. 28.
    Eiglsperger, M., Kaufmann, M., Siebenhaller, M.: A topology-shape-metrics approach for the automatic layout of UML class diagrams. In: Proceedings of the 2003 ACM Symposium on Software Visualization, p. 189. ACM, New York (2003)Google Scholar
  29. 29.
    White, S., Miers, D.: BPMN Modeling and Reference Guide: Understanding and Using BPMN. Future Strategies Inc. (2008)Google Scholar
  30. 30.
    Holschke, O.: Impact of granularity on adjustment behavior in adaptive reuse of business process models. In: Hull, R., Mendling, J., Tai, S. (eds.) BPM 2010. LNCS, vol. 6336, pp. 112–127. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  31. 31.
    Reijers, H.: Design and control of workflow processes: business process management for the service industry. Eindhoven University Press (2003)Google Scholar
  32. 32.
    Dijkman, R., Dumas, M., van Dongen, B., Käärik, R., Mendling, J.: Similarity of business process models: Metrics and evaluation. Inf. Sys. 36, 498–516 (2010)CrossRefGoogle Scholar
  33. 33.
    Dijkman, R., Dumas, M., Garcıa-Banuelos, L., Käärik, R.: Graph Matching Algorithms for Business Process Model Similarity Search. In: Dayal, U., Eder, J., Koehler, J., Reijers, H.A. (eds.) BPM 2009. LNCS, vol. 5701, pp. 48–63. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  34. 34.
    Polyvyanyy, A., Smirnov, S., Weske, M.: On application of structural decomposition for process model abstraction. In: 2nd Int. Conf. BPSC, pp. 110–122 (March 2009)Google Scholar
  35. 35.
    Kop, C., Vöhringer, J., Hölbling, M., Horn, T., Irrasch, C., Mayr, H.: Tool Supported Extraction of Behavior Models. In: Proc. 4th Int. Conf. ISTA (2005)Google Scholar
  36. 36.
    Yue, T., Briand, L., Labiche, Y.: Automatically Deriving a UML Analysis Model from a Use Case Model. Technical report, Carleton University (2009)Google Scholar
  37. 37.
    Wang, H.J., Zhao, J.L., Zhang, L.J.: Policy-Driven Process Mapping (PDPM): Discovering process models from business policies. DSS 48(1), 267–281 (2009)Google Scholar
  38. 38.
    Sinha, A., Paradkar, A.: Use Cases to Process Specifications in Business Process Modeling Notation. In: 2010 IEEE Int. Conf. on Web Services, pp. 473–480 (2010)Google Scholar
  39. 39.
    Shi, L., Mihalcea, R.: Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing. In: Proceedings of the 6th Int. Conf. on Computational Linguistics and Intelligent Text Processing, p. 100 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Fabian Friedrich
    • 1
  • Jan Mendling
    • 2
  • Frank Puhlmann
    • 1
  1. 1.inubit AGBerlinGermany
  2. 2.Humboldt-Universität zu BerlinBerlinGermany

Personalised recommendations