Ryo Yanagimoto | Searcharxiv

arXiv2023

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

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.

cs.HC↗

arXiv2022

Team OS's System for Dialogue Robot Competition 2022

This paper describes our dialogue robot system, OSbot, developed for Dialogue Robot Competition 2022. The dialogue flow is based on state transitions described manually and the transition conditions use the results of keyword extraction and sentiment analysis. The transitions can be easily viewed and edited by managing them on a spreadsheet. The keyword extraction is based on named entity extraction and our predefined keyword set. The sentiment analysis is text-based and uses SVM, which was trained with the multimodal dialogue corpus Hazumi. We quickly checked and edited a dialogue flow by using a logging function. In the competition's preliminary round, our system ended up in third place.

cs.HC↗