Process Model Generation from Natural Language Text

Abstract

Abstract. 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.

Aligning Textual and Graphical Descriptions of Processes Through ILP Techniques

“…(12) In the meantime, the Marketing department makes a request to mail the Zoo Club's magazine to the visitor's home. (13) Once the visitor receives the card, he can go home. that, there is nothing preventing both tasks from getting mapped to the same sentence.…”

“…In general, previous work can be categorized into transformations between models and text (e.g., [11,12] for UML diagrams, or [1,13] for BPMN), and schema [14] or process model [15] matching. Also, there has been work on generating process models from group stories [16] and from use-cases [17], which are less related to this work since they restrict the form of the textual description used to describe the process.…”

“…To validate the quality of the results provided by our tool, we compare them with the ones generated by the approach in [9], on a gold standard from [13] that was later extended by the authors of [9]. We also expanded the gold standard with the last group of models, taken from [13].…”

“…We also expanded the gold standard with the last group of models, taken from [13]. The models in this benchmark were manually analyzed in [13,9] to obtain the correct assignment between tasks and sentences, so that the quality of a tool can be assessed. Table 3 reports the results.…”

Exploring cognitive style and task-specific preferences for process representations

“…Textual documents describing business processes can be policies, reports, forms, manuals, content of knowledge management systems, and e-mail messages [31]. Content management professionals estimated that 85% of the process information in companies is stored in such unstructured format [32].…”