MSENSIS announces that the project under the title Multilingual Chatbot Employing Machine Learning Methods (deepBot) has been approved, and its implementation started by May 2018. The project is co‐financed by the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH–CREATE-INNOVATE (project code: Τ1EDK-05732)
deepBot concerns the design and implementation of a retrieval-based chatbot using state-of-the-art Natural Language Processing (NLP) and Deep Learning methods to better identify the intention of the user along with statistical methods and analytics to better identify the chatbot response.
deepBot will be integrated and tested on the existing UniWay messaging application, the official application of the Greek academic community. The application provides all students of Greek academic institutions with the essential information relevant to their studies (program of study, enrollments, grades, course evaluation, news, etc.). In addition, it provides messaging and file sharing services as it incorporates the relevant FunzyTalk technologies, the first Greek messaging application. Support for messaging services ensures the integration and operation of deepBot's external service into the system. deepBot will support Greek and English languages.
More generally, deepBot concerns the development and commercial exploitation of innovative chatbot services.
The implementation of the project is attended by MSENSIS S.A (coordinator) and UPCOM Ltd. Academic collaborators are the OSWINDS Research Grooup of the Department of Informatics of the Aristotle University of Thessaloniki and the Greek Universities Network (GUnet).