Masakazu Ishihata


2023

pdf bib
Time-Considerable Dialogue Models via Reranking by Time Dependency
Yuiko Tsunomori | Masakazu Ishihata | Hiroaki Sugiyama
Findings of the Association for Computational Linguistics: EMNLP 2023

In the last few years, generative dialogue models have shown excellent performance and have been used for various applications. As chatbots become more prevalent in our daily lives, more and more people expect them to behave more like humans, but existing dialogue models do not consider the time information that people are constantly aware of. In this paper, we aim to construct a time-considerable dialogue model that actively utilizes time information. First, we categorize responses by their naturalness at different times and introduce a new metric to classify responses into our categories. Then, we propose a new reranking method to make the existing dialogue model time-considerable using the proposed metric and subjectively evaluate the performances of the obtained time-considerable dialogue models by humans.