A model-based solution for automated (Re-)engineering of task-oriented chatbots

Chatbots are popular to access all sorts of software services via natural language conversation. The increasing demand for task-oriented chatbots has triggered the proposal of many tools for their construction, like Dialogflow, Lex, Rasa, or Watson. However, selecting the most appropriate one is difficult; the conceptual design behind a chatbot may become buried under the tool technicalities; and migration between chatbot development platforms must be done manually. To alleviate these problems, we propose a platform-independent design notation for task-oriented chatbots, based on the analysis of fifteen chatbot development platforms. Following model-driven engineering principles, the chatbot implementation is synthesised from the design, and designs can be extracted from the implementations, enabling the migration and re-engineering of chatbots. Moreover, a recommender suggests the most suitable platform for a given chatbot design, considering contextual factors. We have realised these ideas in Conga: an extensible web application featuring a design notation editor; a development platform recommender; platform-specific validators; and generators and parsers for Dialogflow and Rasa. We evaluated Conga over 291 Dialogflow and Rasa open-source chatbots, showing its expressiveness, portability, and usefulness for finding chatbot quality issues (found in 93,8% of the chatbots). Overall, our architecture enables neutral chatbot designs, automates migration, and provides mechanisms for defect detection at the design level.