article · Procedia Computer Science
Conversational agents converse with users through natural language and are deployed across sectors such as tourism and healthcare to deliver continuous assistance and perform dedicated tasks. Developing these agents is demanding, as it requires combined expertise in software engineering, machine learning, deep learning, and natural language processing. While commercial and open-source frameworks like Dialogflow and Rasa facilitate construction, recent research introduces model-driven engineering approaches. In particular, domain-specific languages are being designed to reduce designer workload and automate the creation of conversational agents. This overview identifies and outlines conversational agent architectures alongside their core components, evaluates current development platforms, and reviews research on domain-specific languages intended to accelerate and automate implementation.
Conversational agents are increasingly vital for automated customer service and continuous user support. Understanding the software architectures, available tooling, and emerging automation techniques helps organisations choose effective development paths. Highlighting model-driven approaches shows how the technical barriers to building these systems can be lowered, making conversational interfaces faster to design and deploy without requiring specialist teams for every stage.
This work informs software engineers, product designers, and technology transfer teams evaluating conversational agent tooling. By outlining existing platforms and emerging domain-specific languages, it points towards tools that could accelerate software development cycles in fields like tourism and healthcare. Because the abstract describes an overview and review of existing technologies and research directions rather than a newly tested tool, the work represents an early-stage analysis of the development landscape.
AI-generated from the published abstract. Always read the original work before citing.
Conversational agents (CA) are software programs that can converse with users using natural language. They are now widely used in various domains, such as tourism, healthcare, and others, to perform tasks and provide permanent assistance to users by interacting with them in natural language. The development of such applications is a task that requires expertise in several fields, such as software engineering, machine learning, deep learning, and natural language processing (NLP). However, several platforms and frameworks on the market facilitate the building of CA, such as Dialogflow, Rasa, and others. Recently, several research studies have proposed solutions to reduce the workload of developers and designers by offering their model-driven development approaches using domain-specific languages (DSLs), which facilitate the automation of the development of CA. This work aims to provide an Overview of CA to identify and describe their architecture and the details of its key components. and discuss the tools and technologies for their development. At the same time, discover the research topics that focus on using DSLs for model-driven development to automate and speed up the creation of these agents and discover approaches and technologies employed to implement each of these DSLs.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.procs.2023.12.206
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
