no code implementations • 21 Apr 2024 • Donghuo Zeng, Roberto S. Legaspi, Yuewen Sun, Xinshuai Dong, Kazushi Ikeda, Peter Spirtes, Kun Zhang
In this paper, we present a novel approach that tracks a user's latent personality dimensions (LPDs) during ongoing persuasion conversation and generates tailored counterfactual utterances based on these LPDs to optimize the overall persuasion outcome.
no code implementations • 21 Apr 2024 • Donghuo Zeng, Yanan Wang, Kazushi Ikeda, Yi Yu
However, the model training fails to fully explore the space due to the scarcity of training data points, resulting in an incomplete representation of the overall positive and negative distributions.
no code implementations • 20 Oct 2023 • Donghuo Zeng, Kazushi Ikeda
We propose a two-stage training paradigm that guides the model's learning process from semi-hard to hard triplets.
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.
1 code implementation • 1 Feb 2023 • Monisha Singh, Ximi Hoque, Donghuo Zeng, Yanan Wang, Kazushi Ikeda, Abhinav Dhall
The experiments show the usefulness of the proposed dataset.
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.
1 code implementation • 28 Jan 2022 • Takeshi D. Itoh, Takatomi Kubo, Kazushi Ikeda
It is expected that the compositionality in a graph can be associated to the compositionality in the output sequence in many graph2seq tasks.
no code implementations • 2 Mar 2021 • Takeshi D. Itoh, Takatomi Kubo, Kazushi Ikeda
It has an attention pooling layer for each message passing step and computes the final graph representation by unifying the layer-wise graph representations.
no code implementations • 25 Nov 2019 • Jin Watanabe, Takatomi Kubo, Fan Yang, Kazushi Ikeda
An automatic mouse behavior recognition system can considerably reduce the workload of experimenters and facilitate the analysis process.
no code implementations • 23 Oct 2019 • Fan Yang, Jaymar Soriano, Takatomi Kubo, Kazushi Ikeda
One of the complicated relationships among three correlated variables could be a two-layer hierarchical many-to-many mapping.
no code implementations • 14 Jul 2019 • Takeshi D. Itoh, Takatomi Kubo, Kiyoka Ikeda, Yuki Maruno, Yoshiharu Ikutani, Hideaki Hata, Kenichi Matsumoto, Kazushi Ikeda
Program comprehension is a dominant process in software development and maintenance.
no code implementations • 20 Mar 2019 • Yasutaka Furusho, Kazushi Ikeda
The ResNet and the batch-normalization (BN) achieved high performance even when only a few labeled data are available.
1 code implementation • 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2017 • Fan Yang, Jaymar Soriano, Takatomi Kubo, Kazushi Ikeda
There is a considerable demand to apply classification in medical analysis.
no code implementations • 1 Jun 2017 • Matthew J. Holland, Kazushi Ikeda
Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to generalize well.