This paper describes the dialog robot system designed by Team Irisapu for the preliminary round of the Dialogue Robot Competition 2023 (DRC2023). In order to generate dialogue responses flexibly while adhering to predetermined scenarios, we attempted to generate dialogue response sentences using OpenAI's GPT-3. We aimed to create a system that can appropriately respond to users by dividing the dialogue scenario into five sub-scenarios, and creating prompts for each sub-scenario. Also, we incorporated a recovery strategy that can handle dialogue breakdowns flexibly. Our research group has been working on research related to dialogue breakdown detection, and we incorporated our findings to date in this competition. As a result of the preliminary round, a bug in our system affected the outcome and we were not able to achieve a satisfactory result. However, in the evaluation category of "reliability of provided information", we ranked third among all teams.
@article{arxiv.2312.13765,
title = {Team Irisapu Project Description for DRC2023},
author = {Reon Ohashi and Shinjitsu Agatsuma and Kazuya Tsubokura and Yurie Iribe},
journal= {arXiv preprint arXiv:2312.13765},
year = {2023}
}
Comments
This paper is part of the proceedings of the Dialogue Robot Competition 2023