2000 character limit reached
User-adaptive Tourist Information Dialogue System with Yes/No Classifier and Sentiment Estimator (2312.13787v1)
Published 21 Dec 2023 in cs.HC
Abstract: We introduce our system developed for Dialogue Robot Competition 2023 (DRC2023). First, rule-based utterance selection and utterance generation using a LLM are combined. We ensure the quality of system utterances while also being able to respond to unexpected user utterances. Second, dialogue flow is controlled by considering the results of the BERT-based yes/no classifier and sentiment estimator. These allow the system to adapt state transitions and sightseeing plans to the user.
- T. Minato, R. Higashinaka, K. Sakai, T. Funayama, H. Nishizaki, and T. Nagai, “Overview of Dialogue Robot Competition 2023,” in Proceedings of the Dialogue Robot Competition, 2023.
- Y. Kubo, R. Yanagimoto, H. Futase, M. Nakano, Z. Luo, and K. Komatani, “Team OS’s System for Dialogue Robot Competition 2022,” 2022.
- T. Minato, R. Higashinaka, K. Sakai, T. Funayama, H. Nishizaki, and T. Nagai, “Design of a competition specifically for spoken dialogue with a humanoid robot,” Advanced Robotics, vol. 37, no. 21, pp. 1349–1363, 2023.
- K. Komatani and S. Okada, “Multimodal Human-Agent Dialogue Corpus with Annotations at Utterance and Dialogue Levels,” in 9th International Conference on Affective Computing and Intelligent Interaction (ACII), 2021, pp. 1–8.