Article: A collaboration of an ontology and an autoregressive model to build an efficient chatbot model Journal: International Journal of Intelligent Information and Database Systems (IJIIDS) 2024 Vol.16 No.3 pp.241 - 257 Abstract: Question-answer systems are now very popular and crucial to support human in automatically responding frequent questions in many fields. However, these systems depend on learning methods and training data. Therefore, it is necessary to prepare such a good dataset, but it is not an easy job. An ontology-based domain knowledge base is able to help to make nice question-answer pairs and reason semantic information effectively. This study proposes a novel chatbot model involving ontology to generate efficient responses automatically. Besides, an autoregressive model is also employed to complement responses. A case study of admissions advising at the International University - VNU HCMC is taken into account in the proposed chatbot. Experimental results have shown that the collaboration of an ontology-based and autoregressive model-based chatbot is significantly effective. Inderscience Publishers - linking academia, business and industry through research

Title: A collaboration of an ontology and an autoregressive model to build an efficient chatbot model

Authors: Thi Thanh Sang Nguyen; Dang Huu Trong Ho; Ngoc Tram Anh Nguyen; Pham Minh Thu Do

Addresses: School of Computer Science and Engineering, International University, VNU-HCMC; Vietnam National University, Ho Chi Minh City, Vietnam ' School of Computer Science and Engineering, International University, VNU-HCMC; Vietnam National University, Ho Chi Minh City, Vietnam ' School of Computer Science and Engineering, International University, VNU-HCMC; Vietnam National University, Ho Chi Minh City, Vietnam ' School of Computer Science and Engineering, International University, VNU-HCMC; Vietnam National University, Ho Chi Minh City, Vietnam

Abstract: Question-answer systems are now very popular and crucial to support human in automatically responding frequent questions in many fields. However, these systems depend on learning methods and training data. Therefore, it is necessary to prepare such a good dataset, but it is not an easy job. An ontology-based domain knowledge base is able to help to make nice question-answer pairs and reason semantic information effectively. This study proposes a novel chatbot model involving ontology to generate efficient responses automatically. Besides, an autoregressive model is also employed to complement responses. A case study of admissions advising at the International University - VNU HCMC is taken into account in the proposed chatbot. Experimental results have shown that the collaboration of an ontology-based and autoregressive model-based chatbot is significantly effective.

Keywords: ontology; chatbots; answer-question systems; domain knowledge base; deep learning; autoregressive model.

DOI: 10.1504/IJIIDS.2024.137674

International Journal of Intelligent Information and Database Systems, 2024 Vol.16 No.3, pp.241 - 257

Received: 21 Aug 2022
Accepted: 07 Aug 2023
Published online: 02 Apr 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A collaboration of an ontology and an autoregressive model to build an efficient chatbot model

Keep up-to-date