no code implementations • SIGDIAL (ACL) 2021 • Koshiro Okano, Yu Suzuki, Masaya Kawamura, Tsuneo Kato, Akihiro Tamura, Jianming Wu
Responses generated by neural conversational models (NCMs) for non-task-oriented systems are difficult to evaluate.
1 code implementation • 3 Dec 2023 • Xuanhe Zhou, Guoliang Li, Zhaoyan Sun, Zhiyuan Liu, Weize Chen, Jianming Wu, Jiesi Liu, Ruohang Feng, Guoyang Zeng
Database administrators (DBAs) play an important role in managing, maintaining and optimizing database systems.
no code implementations • 22 Feb 2023 • Donghuo Zeng, Jianming Wu, Yanan Wang, Kazunori Matsumoto, Gen Hattori, Kazushi Ikeda
Furthermore, our proposed topic-switch algorithm achieves an average score of 1. 767 and outperforms PLATO-JDS by 0. 267, indicating its effectiveness in improving the user experience of our system.
no code implementations • 7 Nov 2022 • Donghuo Zeng, Yanan Wang, Jianming Wu, Kazushi Ikeda
In this paper, to reduce the interference of hard negative samples in representation learning, we propose a new AV-CMR model to optimize semantic features by directly predicting labels and then measuring the intrinsic correlation between audio-visual data using complete cross-triple loss.
no code implementations • 5 Dec 2021 • Jiwei Zhang, Yi Yu, Suhua Tang, Jianming Wu, Wei Li
On the one hand, audio encoder and visual encoder separately encode audio data and visual data into two different latent spaces.
no code implementations • WS 2017 • Tsuneo Kato, Atsushi Nagai, Naoki Noda, Ryosuke Sumitomo, Jianming Wu, Seiichi Yamamoto
Recursive autoencoders (RAEs) for compositionality of a vector space model were applied to utterance intent classification of a smartphone-based Japanese-language spoken dialogue system.