no code implementations • 9 Oct 2023 • Zhihua Wen, Zhiliang Tian, Wei Wu, Yuxin Yang, Yanqi Shi, Zhen Huang, Dongsheng Li
Finally, we select the most fitting chains of evidence from the evidence forest and integrate them into the generated story, thereby enhancing the narrative's complexity and credibility.
1 code implementation • 26 May 2023 • Lei Guan, Dongsheng Li, Yanqi Shi, Jian Meng
the future weights to update the DNN parameters, making the gradient-based optimizer achieve better convergence and generalization compared to the original optimizer without weight prediction.