Generating Natural Language Texts from Business Process Models

  • Henrik Leopold
  • Jan Mendling
  • Artem Polyvyanyy
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7328)


Process Modeling is a widely used concept for understanding, documenting and also redesigning the operations of organizations. The validation and usage of process models is however affected by the fact that only business analysts fully understand them in detail. This is in particular a problem because they are typically not domain experts. In this paper, we investigate in how far the concept of verbalization can be adapted from object-role modeling to process models. To this end, we define an approach which automatically transforms BPMN process models into natural language texts and combines different techniques from linguistics and graph decomposition in a flexible and accurate manner. The evaluation of the technique is based on a prototypical implementation and involves a test set of 53 BPMN process models showing that natural language texts can be generated in a reliable fashion.


Natural Language Generation Verbalization Business Process Models 


  1. 1.
    Rosemann, M.: Potential Pitfalls of Process Modeling: Part A. Business Process Management Journal 12(2), 249–254 (2006)CrossRefGoogle Scholar
  2. 2.
    Verheijen, G., van Bekkum, J.: NIAM, an information analysis method. In: IFIP WG8.1 Conf. on Comparative Review of Inf. System Method, pp. 537–590 (1982)Google Scholar
  3. 3.
    Nijssen, G., Halpin, T.: Conceptual Schema and Relational Database Design: a fact oriented approach. Prentice-Hall, Inc. (1989)Google Scholar
  4. 4.
    Frederiks, P., Weide, T.: Information modeling: The process and the required competencies of its participants. Data & Knowledge Engineering 58(1), 4–20 (2006)CrossRefGoogle Scholar
  5. 5.
    OMG: Business process model and notation (bpmn) version 2.0. (2011)Google Scholar
  6. 6.
    Reiter, E.: Nlg vs. templates. In: Proceedings of the Fifth European Workshop on Natural Language Generation, pp. 95–106 (1995)Google Scholar
  7. 7.
    Reiter, E., Dale, R.: Building applied natural language generation systems. Nat. Lang. Eng. 3, 57–87 (1997)CrossRefGoogle Scholar
  8. 8.
    Cahill, l., et al.: In search of a reference architecture for nlg systems, 77–85 (1999)Google Scholar
  9. 9.
    van Deemter, K., Krahmer, E., Theune, M.: Real versus Template-Based Natural Language Generation: A False Opposition? Comput. Linguistics 31(1), 15–24 (2005)CrossRefGoogle Scholar
  10. 10.
    Reiter, E., Mellish, C.: Optimizing the costs and benefits of natural language generation. In: IJCAI, pp. 1164–1171 (1993)Google Scholar
  11. 11.
    Galley, M., Fosler-Lussier, E., Potamianos, A.: Hybrid natural language generation for spoken dialogue systems (2001)Google Scholar
  12. 12.
    Reiter, E., Mellish, C., Levine, J., Bridge, S.: Automatic generation of on-line documentation in the idas project. In: ANLP, pp. 64–71 (1992)Google Scholar
  13. 13.
    Leopold, H., Smirnov, S., Mendling, J.: Recognising Activity Labeling Styles in Business Process Models. EMISA 6(1), 16–29 (2011)Google Scholar
  14. 14.
    Leopold, H., Mendling, J., Reijers, H.: On the Automatic Labeling of Process Models. In: Mouratidis, H., Rolland, C. (eds.) CAiSE 2011. LNCS, vol. 6741, pp. 512–520. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  15. 15.
    Vanhatalo, J., Völzer, H., Koehler, J.: The refined process structure tree. Data & Knowledge Engineering 68(9), 793–818 (2009)CrossRefGoogle Scholar
  16. 16.
    Polyvyanyy, A., Vanhatalo, J., Völzer, H.: Simplified Computation and Generalization of the Refined Process Structure Tree. In: Bravetti, M. (ed.) WS-FM 2010. LNCS, vol. 6551, pp. 25–41. Springer, Heidelberg (2011)Google Scholar
  17. 17.
    Meteer, M.W.: Expressibility and the Problem of Efficient Text Planning. St. Martin’s Press, Inc., New York (1992)Google Scholar
  18. 18.
    Stede, M.: Lexicalization in natural language generation: A survey. Artificial Intelligence Review 8, 309–336 (1994)CrossRefGoogle Scholar
  19. 19.
    Dalianis, H.: Aggregation in natural language generation. Computational Intelligence 15(4), 384–414 (1999)CrossRefGoogle Scholar
  20. 20.
    Kibble, R., Power, R.: An integrated framework for text planning and pronominalisation. In: Natural Language Generation, pp. 77–84. ACL (2000)Google Scholar
  21. 21.
    Lavoie, B., Rambow, O.: A fast and portable realizer for text generation systems. In: Applied Natural Language Processing, pp. 265–268. ACL (1997)Google Scholar
  22. 22.
    Busemann, S.: Best-first surface realization. Interface 10 (1996)Google Scholar
  23. 23.
    Goldberg, E., Driedger, N., Kittredge, R.: Using natural-language processing to produce weather forecasts. IEEE Expert 9(2), 45–53 (1994)CrossRefGoogle Scholar
  24. 24.
    Dixon, R.: Deriving Verbs in English. Language Sciences 30(1), 31–52 (2008)CrossRefGoogle Scholar
  25. 25.
    Leopold, H., Smirnov, S., Mendling, J.: Refactoring of Process Model Activity Labels. In: Hopfe, C.J., Rezgui, Y., Métais, E., Preece, A., Li, H. (eds.) NLDB 2010. LNCS, vol. 6177, pp. 268–276. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  26. 26.
    Klein, D., Manning, C.D.: Fast Exact Inference with a Factored Model for Natural Language Parsing. In: NIPS 2003, vol. 15. MIT Press (2003)Google Scholar
  27. 27.
    Miller, G.: WordNet: a lexical database for English. Comm. ACM 38(11), 39–41 (1995)CrossRefGoogle Scholar
  28. 28.
    Mel’cuk, I., Polguère, A.: A formal lexicon in the meaning-text theory (or how to do lexica with words). Computational Linguistics 13(3-4), 261–275 (1987)Google Scholar
  29. 29.
    zur Muehlen, M., Recker, J.: How Much Language Is Enough? Theoretical and Practical Use of the Business Process Modeling Notation. In: Bellahsène, Z., Léonard, M. (eds.) CAiSE 2008. LNCS, vol. 5074, pp. 465–479. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  30. 30.
    Polyvyanyy, A., García-Bañuelos, L., Dumas, M.: Structuring acyclic process models. Information Systems (to appear, 2012)Google Scholar
  31. 31.
    Flesch, R.: How to test readability (1951)Google Scholar
  32. 32.
    Iordanskaja, L., Kittredge, R., Polguére, A.: Lexical selection and paraphrase in a meaning-text generation model. In: Natural Language Generation in Artificial Intelligence and Computational Linguistics, pp. 293–312 (1991)Google Scholar
  33. 33.
    Lavoie, B., Rambow, O., Reiter, E.: The modelexplainer. In: Proceedings of the 8th International Workshop on Natural Language Generation, pp. 9–12 (1996)Google Scholar
  34. 34.
    Meziane, F., Athanasakis, N., Ananiadou, S.: Generating natural language specifications from uml class diagrams. Requirements Engineering 13, 1–18 (2008)CrossRefGoogle Scholar
  35. 35.
    Dalianis, H.: A Method for Validating a Conceptual Model by Natural Language Discourse Generation. In: Loucopoulos, P. (ed.) CAiSE 1992. LNCS, vol. 593, pp. 425–444. Springer, Heidelberg (1992)CrossRefGoogle Scholar
  36. 36.
    Rolland, C., Proix, C.: A Natural Language Approach for Requirements Engineering. In: Loucopoulos, P. (ed.) CAiSE 1992. LNCS, vol. 593, pp. 257–277. Springer, Heidelberg (1992)CrossRefGoogle Scholar
  37. 37.
    Whitley, K.N.: Visual programming languages and the empirical evidence for and against. J. Vis. Lang. Comput. 8(1), 109–142 (1997)CrossRefGoogle Scholar
  38. 38.
    Ottensooser, A., Fekete, A., Reijers, H.A., Mendling, J., Menictas, C.: Making sense of business process descriptions: An experimental comparison of graphical and textual notations. Journal of Systems and Software (to appear, 2012)Google Scholar
  39. 39.
    Mayer, R.: Multimedia Learning, 2nd edn. Cambridge Univ. Press (2009)Google Scholar
  40. 40.
    Ouyang, C., Dumas, M., van der Aalst, W., ter Hofstede, A., Mendling, J.: From business process models to process-oriented software systems. ACM Trans. Softw. Eng. Methodol. 19(1) (2009)Google Scholar
  41. 41.
    Friedrich, F., Mendling, J., Puhlmann, F.: Process Model Generation from Natural Language Text. In: Mouratidis, H., Rolland, C. (eds.) CAiSE 2011. LNCS, vol. 6741, pp. 482–496. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  42. 42.
    OMG: Semantics of Business Vocabulary and Business Rules (SBVR) (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Henrik Leopold
    • 1
  • Jan Mendling
    • 2
  • Artem Polyvyanyy
    • 3
  1. 1.Humboldt-Universität zu BerlinBerlinGermany
  2. 2.WU ViennaViennaAustria
  3. 3.Hasso Plattner InstitutePotsdamGermany

Personalised recommendations