User-adaptive Tourist Information Dialogue System with Yes/No Classifier and Sentiment Estimator

Ryo Yanagimoto; Yunosuke Kubo; Miki Oshio; Mikio Nakano; Kenta Yamamoto; Kazunori Komatani

User-adaptive Tourist Information Dialogue System with Yes/No Classifier and Sentiment Estimator

Human-Computer Interaction 2023-12-22 v1

Authors: Ryo Yanagimoto , Yunosuke Kubo , Miki Oshio , Mikio Nakano , Kenta Yamamoto , Kazunori Komatani

Abstract

We introduce our system developed for Dialogue Robot Competition 2023 (DRC2023). First, rule-based utterance selection and utterance generation using a large language model (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.

Keywords

tourist information dialogue system user-adaptive system large language model yes/no classifier sentiment estimator dialogue flow control drc2023

Cite

@article{arxiv.2312.13787,
  title  = {User-adaptive Tourist Information Dialogue System with Yes/No Classifier and Sentiment Estimator},
  author = {Ryo Yanagimoto and Yunosuke Kubo and Miki Oshio and Mikio Nakano and Kenta Yamamoto and Kazunori Komatani},
  journal= {arXiv preprint arXiv:2312.13787},
  year   = {2023}
}

Comments

This paper is part of the proceedings of the Dialogue Robot Competition 2023

User-adaptive Tourist Information Dialogue System with Yes/No Classifier and Sentiment Estimator

Abstract

Keywords

Cite

Comments

Related papers