2 papers
cs.CL2019
Controllable Dual Skew Divergence Loss for Neural Machine Translation
Zuchao Li, Hai Zhao, Yingting Wu +2
In sequence prediction tasks like neural machine translation, training with cross-entropy loss often leads to models that overgeneralize and plunge into local optima. In this paper…
cs.CL2019
Judging Chemical Reaction Practicality From Positive Sample only Learning
Shu Jiang, Zhuosheng Zhang, Hai Zhao +4
Chemical reaction practicality is the core task among all symbol intelligence based chemical information processing, for example, it provides indispensable clue for further automat…