Search Results for author: Takashi Nose

Found 5 papers, 0 papers with code

Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning

no code implementations31 Jan 2024 Xuecheng Niu, Akinori Ito, Takashi Nose

Therefore, we propose Scheduled Curiosity-Deep Dyna-Q (SC-DDQ), a curiosity-driven curriculum learning framework based on a state-of-the-art model-based reinforcement learning dialog model, Deep Dyna-Q (DDQ).

Efficient Exploration Model-based Reinforcement Learning +2

Construction and Analysis of a Multimodal Chat-talk Corpus for Dialog Systems Considering Interpersonal Closeness

no code implementations LREC 2020 Yoshihiro Yamazaki, Yuya Chiba, Takashi Nose, Akinori Ito

To facilitate research of such dialog systems, we are currently constructing a large-scale multimodal dialog corpus focusing on the relationship between speakers.

TAG

Improving User Impression in Spoken Dialog System with Gradual Speech Form Control

no code implementations WS 2018 Yukiko Kageyama, Yuya Chiba, Takashi Nose, Akinori Ito

In this paper, we conduct dialog experiments and show that controlling the form of system utterances can improve the users{'} impression.

Cannot find the paper you are looking for? You can Submit a new open access paper.