Team Flow at DRC2023: Building Common Ground and Text-based Turn-taking in a Travel Agent Spoken Dialogue System
This work addresses the challenge of enhancing spoken dialogue systems for travel agents, but it appears incremental as it builds on existing competition frameworks without introducing major breakthroughs.
The paper tackled the problem of improving dialogue robots' capability by developing a system that builds common ground and enables text-based turn-taking for more natural interactions, resulting in a system that generates sightseeing spot search queries and waits for user comprehension during dialogue.
At the Dialogue Robot Competition 2023 (DRC2023), which was held to improve the capability of dialogue robots, our team developed a system that could build common ground and take more natural turns based on user utterance texts. Our system generated queries for sightseeing spot searches using the common ground and engaged in dialogue while waiting for user comprehension.