Generating Natural Language Texts from Business Process Models

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.

[1]  John A. Bateman,et al.  Expressibility and the problem of efficient text planning , 1996, Machine Translation.

[2]  Eduard H. Hovy,et al.  Aggregation in Natural Language Generation , 1993, EWNLG.

[3]  Dan Klein,et al.  A* Parsing: Fast Exact Viterbi Parse Selection , 2003, NAACL.

[4]  Richard Power,et al.  An integrated framework for text planning and pronominalisation , 2000, INLG.

[5]  Alain Polguère,et al.  Lexical Selection and Paraphrase in a Meaning-Text Generation Model , 1991 .

[6]  Daniel S. Paiva,et al.  In search of a reference architecture for NLG systemsLynne , 1999 .

[7]  Richard E. Mayer,et al.  Multimedia Learning , 2001, Visible Learning Guide to Student Achievement.

[8]  Theo P. van der Weide,et al.  Information modeling: The process and the required competencies of its participants , 2004, Data Knowl. Eng..

[9]  Kirsten N. Whitley.  Visual Programming Languages and the Empirical Evidence For and Against , 1997, J. Vis. Lang. Comput..

[10]  G. M. Nijssen,et al.  Conceptual schema and relational database design - a fact oriented approach , 1989 .

[11]  Jan Mendling,et al.  On the Automatic Labeling of Process Models , 2011, CAiSE.

[12]  Marlon Dumas,et al.  Structuring acyclic process models , 2010, Inf. Syst..

[13]  Owen Rambow,et al.  The ModelExplainer , 1996, INLG.

[14]  Maguelonne Teisseire,et al.  Natural Language Processing and Information Systems , 2014, Lecture Notes in Computer Science.

[15]  Michael Rosemann,et al.  Potential pitfalls of process modeling: part A , 2006, Bus. Process. Manag. J..

[16]  R. Flesch.  How to test readability , 1951 .

[17]  Stephan Busemann,et al.  Best-First Surface Realization , 1996, INLG.

[18]  Angel R. Martinez,et al.  Natural language processing , 2010 .

[19]  Jan Mendling,et al.  From business process models to process-oriented software systems , 2009, TSEM.

[20]  Robert Dixon,et al.  Deriving verbs in English , 2008 .

[21]  J. J. V. R. Wintraecken,et al.  The NIAM Information Analysis Method , 1990, Springer Netherlands.

[22]  Sophia Ananiadou,et al.  Generating Natural Language specifications from UML class diagrams , 2008, Requirements Engineering.

[23]  Colette Rolland,et al.  A Natural Language Approach for Requirements Engineering , 1992, CAiSE.

[24]  Emiel Krahmer,et al.  Squibs and Discussions: Real versus Template-Based Natural Language Generation: A False Opposition? , 2005, CL.

[25]  Robert Dale,et al.  Building applied natural language generation systems , 1997, Natural Language Engineering.

[26]  Alain Polguère,et al.  A Formal Lexicon in the Meaning-Text Theory (or How to Do Lexica with Words) , 1987, Comput. Linguistics.

[27]  George A. Miller.  WordNet: A Lexical Database for English , 1992, HLT.

[28]  Chris Mellish,et al.  Optimizing the Costs and Benefits of Natural Language Generation , 1993, International Joint Conference on Artificial Intelligence.

[29]  Jan Mendling,et al.  Refactoring of Process Model Activity Labels , 2010, NLDB.

[30]  Richard I. Kittredge,et al.  Using natural-language processing to produce weather forecasts , 1994, IEEE Expert.

[31]  Eric Fosler-Lussier,et al.  Hybrid natural language generation for spoken dialogue systems , 2001, INTERSPEECH.

[32]  Hercules Dalianis.  A Method for Validating a Conceptual Model by Natural Language Discourse Generation , 1992, CAiSE.

[33]  Dan Klein,et al.  Fast Exact Inference with a Factored Model for Natural Language Parsing , 2002, NIPS.

[34]  Jussi Vanhatalo,et al.  Simplified Computation and Generalization of the Refined Process Structure Tree , 2010, WS-FM.

[35]  Jan Mendling,et al.  Making sense of business process descriptions: An experimental comparison of graphical and textual notations , 2012, J. Syst. Softw..

[36]  Manfred Stede,et al.  Lexicalization in natural language generation: A survey , 1994, Artificial Intelligence Review.

[37]  Benoit Lavoie,et al.  A Fast and Portable Realizer for Text Generation Systems , 1997, ANLP.

[38]  John Levine,et al.  Automatic Generation of On-Line Documentation in the IDAS Project , 1992, ANLP.

[39]  Jana Koehler,et al.  The refined process structure tree , 2008, Data Knowl. Eng..

[40]  Jan Mendling,et al.  Recognising Activity Labeling Styles in Business Process Models , 2011, Enterp. Model. Inf. Syst. Archit. Int. J. Concept. Model..

[41]  Jan Mendling,et al.  Process Model Generation from Natural Language Text , 2011, CAiSE.

[42]  William C. Mann,et al.  Natural Language Generation in Artificial Intelligence and Computational Linguistics , 1990 .

[43]  Ehud Reiter,et al.  NLG vs. Templates , 1995, ArXiv.

[44]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[45]  Jan Recker,et al.  How Much Language Is Enough? Theoretical and Practical Use of the Business Process Modeling Notation , 2008, CAiSE.