Tourist Guidance Robot Based on HyperCLOVA
This work addresses the problem of creating effective tourist guidance robots for users in specific competition settings, but it is incremental as it builds on existing models and methods.
The authors tackled the challenge of building a tourist guidance robot by combining rule-based and generation-based dialog systems, leveraging HyperCLOVA for tasks like response generation and summarization, and achieved second place in the preliminary round of the Dialogue Robot Competition 2022, advancing to the finals.
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.