BPM2Text: A language independent framework for Business Process Models to Natural Language Text
Resumo
The proper representation of a Business process is important for its execution and understanding. BPMN has been used as the standard notation for business process models, however domain specialists, which are experts in the business, do not have necessarily the modeling skills to easily read a business process model. It is easier for them to read in natural language. In this work, we propose a language-independent framework, instantiated using Java standard technology, for generating automatically natural language texts from business process models. A case study was conducted to evaluate the quality of the generated text. We found empirical support that the textual work instructions can be considered equivalent, in terms of knowledge representation, to process models represented in BPMN. Regarding the framework output quality (textual descriptions) 86% of the subjects claims that it vary from excellent to good.Downloads
Referências
Bajwa, I. S. and Choudhary, M. A. (2006). Natural language processing based automated system
for uml diagrams generation. In The 18th Saudi National Computer Conf. on computer science (NCC18). Riyadh, Saudi Arabia: The Saudi Computer Society (SCS).
Busch, M. (1993). Using likert scales in l2 research a researcher comments. TESOL Quarterly,
(4):733–736.
Busemann, S. (1996). Best First Surface Realization. DFKI.
Dale, R. and Reiter, E. (2000). Building natural language generation systems. Cambridge University
Press.
Dumas, M., La Rosa, M., Mendling, J., and Reijers, H. A. (2013). Fundamentals of business
process management. Springer.
Ehud Reiter, R. D. (1997). Building applied natural language generation systems. Natural Language
Engineering 1.
Figl, K. and Laue, R. (2011). Cognitive complexity in business process modeling. In Advanced
Information Systems Engineering, pages 452–466. Springer.
Friedrich, F., Mendling, J., and Puhlmann, F. (2011). Process model generation from natural
language text. In Advanced Information Systems Engineering, pages 482–496. Springer.
Galley, M., Fosler-Lussier, E., and Potamianos, A. (2001). Hybrid natural language generation for
spoken dialogue systems. In INTERSPEECH, pages 1735–1738.
Kettinger, W. J., Teng, J. T., and Guha, S. (1997). Business process change: a study of methodologies,
techniques, and tools. MIS quarterly, pages 55–80.
Larman, C. (2005). Applying uml and patterns: An introduction to object-oriented analysis and
design and iterative development.
Leao, F., Revoredo, K., and Bai ˜ ao, F. (2013). Learning well-founded ontologies through word ˜
sense disambiguation. In Intelligent Systems (BRACIS), 2013 Brazilian Conference on, pages
–200. IEEE.
Leopold, H., Eid-Sabbagh, R.-H., Mendling, J., Azevedo, L. G., and Baiao, F. A. (2013). Detection ˜
of naming convention violations in process models for different languages. Decision Support
Systems, 56:310–325.
Leopold, H., Mendling, J., and Polyvyanyy, A. (2012). Generating natural language texts
from business process models. In Advanced Information Systems Engineering, pages 64–79.
Springer.
Martin, J. H. and Jurafsky, D. (2000). Speech and language processing.
Mel’cuk, I. A. and Polguere, A. (1987). A formal lexicon in the meaning-text theory:(or how to ˇ
do lexica with words). Computational linguistics, 13(3-4):261–275.
Mendling, J., Strembeck, M., and Recker, J. (2012). Factors of process model comprehension
findings from a series of experiments. Decision Support Systems, 53(1):195–206.
Paas, F., Renkl, A., and Sweller, J. (2003). Cognitive load theory and instructional design: Recent
developments. Educational psychologist, 38(1):1–4.
Polyvyanyy, A., Vanhatalo, J., and Volzer, H. (2011). Simplified computation and generaliza- ¨
tion of the refined process structure tree. In Web Services and Formal Methods, pages 25–41.
Springer.
Pree, W. (1994). Meta patterns a means for capturing the essentials of reusable object-oriented
design. In Object-oriented programming, pages 150–162. Springer.
Recker, J. (2012). Scientific research in information systems: a beginner’s guide. Springer.
Reijers, H. A. and Mendling, J. (2011). A study into the factors that influence the understandability
of business process models. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE
Transactions on, 41(3):449–462.
Reiter, E. (1995). Nlg vs. templates. arXiv preprint cmp-lg/9504013.
Reiter, E. and Mellish, C. (1993). Optimizing the costs and benefits of natural language generation.
In IJCAI, pages 1164–1171.
Reiter, E., Mellish, C., and Levine, J. (1992). Automatic generation of on-line documentation in
the idas project. In Proceedings of the third conference on Applied natural language processing,
pages 64–71. Association for Computational Linguistics.
Rodrigues, R., Azevedo, L., Revoredo, K., and Leopold, H. (2014). A tool to generate natural
language text from business process models. In CBSoft 2014 - Tool Session.
Van Deemter, K., Krahmer, E., and Theune, M. (2005). Real versus template-based natural language
generation: A false opposition? Computational Linguistics, 31(1):15–24.
Vanhatalo, J., Volzer, H., and Koehler, J. (2009). The refined process structure tree. ¨ Data &
Knowledge Engineering, 68(9):793–818.
