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.
Cite
@article{arxiv.2210.10400,
title = {Tourist Guidance Robot Based on HyperCLOVA},
author = {Takato Yamazaki and Katsumasa Yoshikawa and Toshiki Kawamoto and Masaya Ohagi and Tomoya Mizumoto and Shuta Ichimura and Yusuke Kida and Toshinori Sato},
journal= {arXiv preprint arXiv:2210.10400},
year = {2022}
}
Comments
This paper is part of the proceedings of the Dialogue Robot Competition 2022