Multi-view support vector machine classifier via L0/1 soft-margin loss with structural information

C Chen, Q Liu, R Xu, Y Zhang, H Wang, Q Yu - Information Fusion, 2025 - Elsevier
Multi-view learning seeks to leverage the advantages of various views to complement each
other and make full use of the latent information in the data. Nevertheless, effectively …

Heterogeneous-branch collaborative learning for dialogue generation

Y Li, S Feng, B Sun, K Li - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
With the development of deep learning, advanced dialogue generation methods usually
require a greater amount of computational resources. One promising approach to obtaining …

Modeling Complex Dialogue Map**s via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder

B Sun, S Feng, Y Li, W Wang, F Mi, Y Li, K Li - ar**s (CDM), including one-to-many and many-to-one map**s,
tend to make dialogue models generate incoherent or dull responses, and modeling these …