Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation. EMNLP2017.

Release time:2024-01-09

Hits:

First Author:: Baosong Yang, Derek F. Wong, Tong Xiao, Lidia S. Chao, Jingbo Zhu.

Translation or Not:: no

Pre One:Fast Parallel Training of Neural Language Models. IJCAI2017.
Next One:Analysis of Data Parallel Methods in Training Neural Language Models via Multiple GPUs. CWMT2017.