Grant: Engage Grants Program
University of New Brunswick
$25,000.00
An adaptable natural language understanding module for conversational agents
EF 2019-20
Résumé
For over five years, Massively.ai has been leading the development of some of the world's most engaging chatbots, combining conversational design, natural language processing, and machine learning techniques. Currently, a document retrieval algorithm is used to answer questions submitted to these conversational agents. While this is effective, the market continues to demand higher accuracy, and more flexibility and user-friendliness, for an improved overall user experience.The goal of this project is to support the development of a novel and adaptable natural language understanding module, incorporating a keyword model, intent classification, and intent extraction. Such a module, once fully tested and deployed, will help to improve the accuracy of answers provided by conversational agents. One key requirement is for this approach to be fully automated. A new client could submit their data to the system, the system could be trained on this new data set, and the results could be integrated into the chatbot platform. This next-generation natural language system would have a wide range of applications, including robotics, banking, and potential projects with a focus on education and environmental awareness.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
New Brunswick, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
543974-2019
Name nom
Fleming, Michael
Department département
Computer Science, Faculty of
Organization id
75
Institution établissement
University of New Brunswick
Province en
New Brunswick
Province fr
Nouveau-Brunswick
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2019
Competition year année de concours
2019
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
1551
Committee name en
Atlantic Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Atlantique
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2801
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Natural language and speech understanding
Research subject fr
Langage naturel et reconnaissance de la parole
Installment
inst:1 - 1
Partie
1
Nb partie
1
Application title
An adaptable natural language understanding module for conversational agents
Keyword
NSERC
Application summary
For over five years, Massively.ai has been leading the development of some of the world's most engaging chatbots, combining conversational design, natural language processing, and machine learning techniques. Currently, a document retrieval algorithm is used to answer questions submitted to these conversational agents. While this is effective, the market continues to demand higher accuracy, and more flexibility and user-friendliness, for an improved overall user experience.The goal of this project is to support the development of a novel and adaptable natural language understanding module, incorporating a keyword model, intent classification, and intent extraction. Such a module, once fully tested and deployed, will help to improve the accuracy of answers provided by conversational agents. One key requirement is for this approach to be fully automated. A new client could submit their data to the system, the system could be trained on this new data set, and the results could be integrated into the chatbot platform. This next-generation natural language system would have a wide range of applications, including robotics, banking, and potential projects with a focus on education and environmental awareness.