To improve the interactive capabilities of a dialogue system, e.g., to adapt to different customers, the Dialogue Robot Competition (DRC2022) was held. As one of the teams, we built a dialogue system with a pipeline structure containing four modules. The natural language understanding (NLU) and natural language generation (NLG) modules were GPT-2 based models, and the dialogue state tracking (DST) and policy modules were designed on the basis of hand-crafted rules. After the preliminary round of the competition, we found that the low variation in training examples for the NLU and failed recommendation due to the policy used were probably the main reasons for the limited performance of the system.
@article{arxiv.2210.09518,
title = {Team Flow at DRC2022: Pipeline System for Travel Destination Recommendation Task in Spoken Dialogue},
author = {Ryu Hirai and Atsumoto Ohashi and Ao Guo and Hideki Shiroma and Xulin Zhou and Yukihiko Tone and Shinya Iizuka and Ryuichiro Higashinaka},
journal= {arXiv preprint arXiv:2210.09518},
year = {2022}
}
Comments
This paper is part of the proceedings of the Dialogue Robot Competition 2022