Natural language techniques supporting decision modelers
- PDF / 1,690,928 Bytes
- 31 Pages / 439.37 x 666.142 pts Page_size
- 62 Downloads / 227 Views
Natural language techniques supporting decision modelers Leticia Arco1,2 · Gonzalo Nápoles2 · Frank Vanhoenshoven2 · Ana Laura Lara3 · Gladys Casas4 · Koen Vanhoof2 Received: 21 March 2019 / Accepted: 20 October 2020 © The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature 2020
Abstract Decision Model and Notation (DMN) has become a relevant topic for organizations since it allows users to control their processes and organizational decisions. The increasing use of DMN decision tables to capture critical business knowledge raises the need for supporting analysis tasks such as the extraction of inputs, outputs and their relations from natural language descriptions. In this paper, we create a stepping stone towards implementing a Natural Language Processing framework to model decisions based on the DMN standard. Our proposal contributes to the generation of decision rules and tables from a single sentence analysis. This framework comprises three phases: (1) discourse and semantic analysis, (2) syntactic analysis and (3) decision table construction. To the best of our knowledge, this is the first attempt devoted to automatically discovering decision rules according to the DMN terminology from natural language descriptions. Aiming at assessing the quality of the resultant decision tables, we have conducted a survey involving 16 DMN experts. The results have shown that our framework is able to generate semantically correct tables. It is convenient to mention that our proposal does not aim to replace analysts but support them in creating better models with less effort. Keywords Decision Modeling and Notation · Decision rules · Decision tables · Natural Language Processing
Responsible editor: Hendrik Blockeel
B
Leticia Arco [email protected]
1
AI Lab, Computer Science Department, Vrije Universiteit Brussel, Pleinlaan 9, 3rd floor, 1050 Brussels, Belgium
2
Business Informatics Group, Faculty of Business Economics, Hasselt University, Diepenbeek Kantoor A50, Hasselt, Belgium
3
AI Lab, Computer Science Department, Central University of Las Villas, Carretera a Camajuaní km 5 1/2, Santa Clara, Villa Clara, Cuba
4
Weast Coast University , Miami Campus, 9250 NW 36th St, Doral, FL 33178, USA
123
L. Arco et al.
1 Introduction To facilitate communication on and analysis of process logic and decision logic, businesses often rely on representations such as process diagrams and decision tables. The graphical Business Process Model and Notation (BPMN)1 that has been developed explicitly for process modeling has been recently complemented with the addition of Decision Modelling and Notation (DMN),2 aimed explicitly at decision modeling. It is the job of a business analyst to create these processes and decision models based on the knowledge it has gathered from, for example, observations, interviews, policy documents, regulatory documents and legacy code (IIBA 2009). Gathering the business rules needed to model the decisions has been coined rule harvesting (Boyer and Mili 2011)
Data Loading...
