Section: Computer Science and Engineering
Tutor: TANCA LETIZIA
Advisor: PERNICI BARBARA Major Research topic
:Data Driven ChatbotsAbstract:
This is a joint research between Politecnico di Milano and IBM italy and It is about developing data-driven chatbots and devising a new approach for improving the quality and effectiveness of training in the context of Industry 4.0.
Chatbots and conversational interfaces are becoming ubiquitous and a new HCI paradigm to access applications and information. This thesis proposes a novel approach for the development of “data-driven chatbots”. Key ingredients are “meta-conversation”, “conversation tables” (controlling the interface ), and a “conversation engine”. Several advantages are envisioned:
(i) the lower effort for developing new conversational applications;
(ii) easiness of maintenance and update, and therefore improved quality;
(iii) possibility for content experts of developing conversational applications, without the need of ICT experts.
This research aims to replicate results in a learning framework between Learner, Course, Teacher, and chatbot. A chatbot technology should be designed to support educational, domain-independent, data-driven chatbots. Several concepts of the meta-modeling are related to organizing the chatbot's wording. Linguistic formulations correspond to single text replies and act as the basic building block of the chatbot's wording. A separate line of future research might be to look more at what the chatbot could bring to the virtual world.