no code implementations • COLING 2022 • Xuantao Lu, Jingping Liu, Zhouhong Gu, Hanwen Tong, Chenhao Xie, Junyang Huang, Yanghua Xiao, Wenguang Wang
In this paper, we propose a scoring model to automatically learn a model-based reward, and an effective training strategy based on curriculum learning is further proposed to stabilize the training process.
no code implementations • 2 Aug 2021 • Junyang Huang, Yongbo Wang, Yongliang Wang, Yang Dong, Yanghua Xiao
It first learns relation embedding over the schema entities and question words with predefined schema relations with ELECTRA and relation aware transformer layer as backbone.
1 code implementation • 27 Jun 2021 • Junyang Huang, Changxing Ding
Firstly, to reduce the difficulty of directly transforming the profile face features into a frontal pose, we propose to learn the feature residual between the source pose and its nearby pose in a block-byblock fashion, and thus traversing to the feature space of a smaller pose by adding the learned residual.