activity
20182021
most citedTransformer-based Spatial-Temporal Feature Learning for EEG Decoding

93 citations · 117 across the 4 of their papers we have counts for

collaborators

8 papers

cs.IR20211 cited

Improving Sequential Recommendation Consistency with Self-Supervised Imitation

Xu Yuan, Hongshen Chen, Yonghao Song +4

Most sequential recommendation models capture the features of consecutive items in a user-item interaction history. Though effective, their representation expressiveness is still h…

eess.SP202193 cited

Transformer-based Spatial-Temporal Feature Learning for EEG Decoding

Yonghao Song, Xueyu Jia, Lie Yang +1

At present, people usually use some methods based on convolutional neural networks (CNNs) for Electroencephalograph (EEG) decoding. However, CNNs have limitations in perceiving glo…

cs.LG202114 cited

Common Spatial Generative Adversarial Networks based EEG Data Augmentation for Cross-Subject Brain-Computer Interface

Yonghao Song, Lie Yang, Xueyu Jia +1

The cross-subject application of EEG-based brain-computer interface (BCI) has always been limited by large individual difference and complex characteristics that are difficult to p…

cs.CL2020

Group-wise Contrastive Learning for Neural Dialogue Generation

Hengyi Cai, Hongshen Chen, Yonghao Song +4

Neural dialogue response generation has gained much popularity in recent years. Maximum Likelihood Estimation (MLE) objective is widely adopted in existing dialogue model learning.…

cs.CL2020

Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight

Hengyi Cai, Hongshen Chen, Yonghao Song +3

Current state-of-the-art neural dialogue models learn from human conversations following the data-driven paradigm. As such, a reliable training corpus is the crux of building a rob…

cs.CL2020

Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation

Hengyi Cai, Hongshen Chen, Cheng Zhang +5

Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of huma…