A Graphical DSL for Accelerating Chatbot Development
Charaf Ouaddi, Lamya Benaddi, Lahbib Naimi, El Mahi Bouziane, Abdeslam Jakimi
Abstract
The development of chatbots utilizing artificial intelligence (AI) techniques represents a significant advancement in Natural Language Processing (NLP). Numerous studies employ deep learning and NLP methodologies to construct sophisticated chatbot systems. Additionally, developers and companies often utilize APIs provided by intent recognition services like Dialogflow and Amazon Lex to easily create chatbots using graphical forms, which enhance chatbot functionality. However, these APIs have limitations, such as potential dependency on specific NLP service providers and associated high costs. To address these limitations, the proposed work addresses critical gaps in chatbot development tools by constructing a Domain-Specific Language (DSL) for chatbot development. This DSL aims to simplify the chatbot development process and reduce costs. Specifically, the paper introduces a graphical DSL designed to accelerate chatbot development. We use code generation templates to easily generate the source code for chatbots of the Rasa framework, simplifying the development process and reducing the time spent on manual coding.