1 code implementation • 16 Aug 2021 • Yuhao Cui, Zhou Yu, Chunqi Wang, Zhongzhou Zhao, Ji Zhang, Meng Wang, Jun Yu
Nevertheless, most existing VLP approaches have not fully utilized the intrinsic knowledge within the image-text pairs, which limits the effectiveness of the learned alignments and further restricts the performance of their models.
1 code implementation • EMNLP 2018 • Chunqi Wang, Ji Zhang, Haiqing Chen
Existing approaches to neural machine translation are typically autoregressive models.
1 code implementation • IJCNLP 2017 • Chunqi Wang, Bo Xu
The first is that they heavily rely on manually designed bigram feature, i. e. they are not good at capturing n-gram features automatically.