Tourist Guidance Robot Based on HyperCLOVA
Yamazaki, Takato, Yoshikawa, Katsumasa, Kawamoto, Toshiki, Ohagi, Masaya, Mizumoto, Tomoya, Ichimura, Shuta, Kida, Yusuke, Sato, Toshinori
–arXiv.org Artificial Intelligence
This paper describes our system submitted to Dialogue Robot Competition 2022. Our proposed system is a combined model of rule-based and generation-based dialog systems. The system utilizes HyperCLOVA, a Japanese foundation model, not only to generate responses but also summarization, search information, etc. We also used our original speech recognition system, which was fine-tuned for this dialog task. As a result, our system ranked second in the preliminary round and moved on to the finals.
arXiv.org Artificial Intelligence
Oct-19-2022
- Country:
- Asia > Japan
- Honshū > Kantō > Tokyo Metropolis Prefecture > Tokyo (0.18)
- North America > Dominican Republic (0.04)
- Asia > Japan
- Genre:
- Personal > Interview (0.46)
- Research Report (0.64)
- Industry:
- Education (0.50)
- Technology:
- Information Technology > Artificial Intelligence
- Natural Language (1.00)
- Representation & Reasoning > Rule-Based Reasoning (0.49)
- Robots (1.00)
- Speech > Speech Recognition (0.56)
- Information Technology > Artificial Intelligence