2 papers
cs.CL2018
Generalize Symbolic Knowledge With Neural Rule Engine
Shen Li, Hengru Xu, Zhengdong Lu
As neural networks have dominated the state-of-the-art results in a wide range of NLP tasks, it attracts considerable attention to improve the performance of neural models by integ…
cs.CL2018
From Random to Supervised: A Novel Dropout Mechanism Integrated with Global Information
Hengru Xu, Shen Li, Renfen Hu +2
Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training. Inspired by dropout, this paper presents GI-Dropout, a novel dropout metho…