KJCKorea
Journal Central

@article{ART002927608},
author={Chae-Lim Park and So-Yeop Yoo and Ok-Ran Jeong},
title={A Study on Conversational AI Agent based on Continual Learning},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2023},
volume={28},
number={1},
pages={27-38},
doi={10.9708/jksci.2023.28.01.027}

TY - JOUR
AU - Chae-Lim Park
AU - So-Yeop Yoo
AU - Ok-Ran Jeong
TI - A Study on Conversational AI Agent based on Continual Learning
JO - Journal of The Korea Society of Computer and Information
PY - 2023
VL - 28
IS - 1
PB - The Korean Society Of Computer And Information
SP - 27
EP - 38
SN - 1598-849X
AB - In this paper, we propose a conversational AI agent based on continual learning that can continuously learn and grow with new data over time. A continual learning-based conversational AI agent consists of three main components: Task manager, User attribute extraction, and Auto-growing knowledge graph. When a task manager finds new data during a conversation with a user, it creates a new task with previously learned knowledge. The user attribute extraction model extracts the user’s characteristics from the new task, and the auto-growing knowledge graph continuously learns the new external knowledge. Unlike the existing conversational AI agents that learned based on a limited dataset, our proposed method enables conversations based on continuous user attribute learning and knowledge learning. A conversational AI agent with continual learning technology can respond personally as conversations with users accumulate. And it can respond to new knowledge continuously. This paper validate the possibility of our proposed method through experiments on performance changes in dialogue generation models over time.
KW - Dialogue system;Conversational AI agent;Continual learning;Chatbots;Knowledge graph
DO - 10.9708/jksci.2023.28.01.027
ER -

Chae-Lim Park, So-Yeop Yoo and Ok-Ran Jeong. (2023). A Study on Conversational AI Agent based on Continual Learning. Journal of The Korea Society of Computer and Information, 28(1), 27-38.

Chae-Lim Park, So-Yeop Yoo and Ok-Ran Jeong. 2023, "A Study on Conversational AI Agent based on Continual Learning", Journal of The Korea Society of Computer and Information, vol.28, no.1 pp.27-38. Available from: doi:10.9708/jksci.2023.28.01.027

Chae-Lim Park, So-Yeop Yoo, Ok-Ran Jeong "A Study on Conversational AI Agent based on Continual Learning" Journal of The Korea Society of Computer and Information 28.1 pp.27-38 (2023) : 27.

Chae-Lim Park, So-Yeop Yoo, Ok-Ran Jeong. A Study on Conversational AI Agent based on Continual Learning. 2023; 28(1), 27-38. Available from: doi:10.9708/jksci.2023.28.01.027

Chae-Lim Park, So-Yeop Yoo and Ok-Ran Jeong. "A Study on Conversational AI Agent based on Continual Learning" Journal of The Korea Society of Computer and Information 28, no.1 (2023) : 27-38.doi: 10.9708/jksci.2023.28.01.027

Chae-Lim Park; So-Yeop Yoo; Ok-Ran Jeong. A Study on Conversational AI Agent based on Continual Learning. Journal of The Korea Society of Computer and Information, 28(1), 27-38. doi: 10.9708/jksci.2023.28.01.027

Chae-Lim Park; So-Yeop Yoo; Ok-Ran Jeong. A Study on Conversational AI Agent based on Continual Learning. Journal of The Korea Society of Computer and Information. 2023; 28(1) 27-38. doi: 10.9708/jksci.2023.28.01.027

Chae-Lim Park, So-Yeop Yoo, Ok-Ran Jeong. A Study on Conversational AI Agent based on Continual Learning. 2023; 28(1), 27-38. Available from: doi:10.9708/jksci.2023.28.01.027

Chae-Lim Park, So-Yeop Yoo and Ok-Ran Jeong. "A Study on Conversational AI Agent based on Continual Learning" Journal of The Korea Society of Computer and Information 28, no.1 (2023) : 27-38.doi: 10.9708/jksci.2023.28.01.027