Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Tourist Guidance Robot Based on HyperCLOVA (2210.10400v1)

Published 19 Oct 2022 in cs.CL

Abstract: 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.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Takato Yamazaki (5 papers)
  2. Katsumasa Yoshikawa (3 papers)
  3. Toshiki Kawamoto (3 papers)
  4. Masaya Ohagi (4 papers)
  5. Tomoya Mizumoto (10 papers)
  6. Shuta Ichimura (2 papers)
  7. Yusuke Kida (10 papers)
  8. Toshinori Sato (4 papers)
Citations (4)

Summary

We haven't generated a summary for this paper yet.