3 citations · 3 across the 5 of their papers we have counts for
6 papers
Supporting Perspective Acquisition and Opinion Formation on Societal Issues Through AI-Generated Japanese Rap Battle Debates
Ryota Mibayashi, Toru Urakawa, Dai Takanashi +9
Acquiring diverse perspectives and forming informed opinions on societal issues are essential for critical thinking and informed decision-making. Although observing debates between…
QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement
Shogo Yamauchi, Hideaki Tamori, Makoto Sakai +2
We propose a parameter-efficient speech enhancement framework, Quaternion Conformer GAN (QC-GAN), which combines a Quaternion Conformer generator with MetricGAN-based training. The…
Quaternion Self-Attention with Shared Scores
Shogo Yamauchi, Tohru Nitta, Hideaki Tamori
Quaternion neural networks are parameter-efficient and model multidimensional dependencies by representing four related features as a single entity. However, existing quaternion se…
Prestige bias drives the viral spread of content reposted by influencers in online communities
Takuro Niitsuma, Mitsuo Yoshida, Hideaki Tamori +1
Cultural evolution theory suggests that prestige bias - whereby individuals preferentially learn from prestigious figures - has played a key role in human ecological success. Howev…
Transformer-based Lexically Constrained Headline Generation
Kosuke Yamada, Yuta Hitomi, Hideaki Tamori +4
This paper explores a variant of automatic headline generation methods, where a generated headline is required to include a given phrase such as a company or a product name. Previo…
A Large-Scale Multi-Length Headline Corpus for Analyzing Length-Constrained Headline Generation Model Evaluation
Yuta Hitomi, Yuya Taguchi, Hideaki Tamori +5
Browsing news articles on multiple devices is now possible. The lengths of news article headlines have precise upper bounds, dictated by the size of the display of the relevant dev…