8 citations · 27 across the 10 of their papers we have counts for
7 papers · 1 filter
MolXPT: Wrapping Molecules with Text for Generative Pre-training
Zequn Liu, Wei Zhang, Yingce Xia +5
Generative pre-trained Transformer (GPT) has demonstrates its great success in natural language processing and related techniques have been adapted into molecular modeling. Conside…
UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost
Zhen Wu, Lijun Wu, Qi Meng +5
Transformer architecture achieves great success in abundant natural language processing tasks. The over-parameterization of the Transformer model has motivated plenty of works to a…
IOT: Instance-wise Layer Reordering for Transformer Structures
Jinhua Zhu, Lijun Wu, Yingce Xia +5
With sequentially stacked self-attention, (optional) encoder-decoder attention, and feed-forward layers, Transformer achieves big success in natural language processing (NLP), and…
Microsoft Research Asia's Systems for WMT19
Yingce Xia, Xu Tan, Fei Tian +11
We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place fo…
Efficient Bidirectional Neural Machine Translation
Xu Tan, Yingce Xia, Lijun Wu +1
The encoder-decoder based neural machine translation usually generates a target sequence token by token from left to right. Due to error propagation, the tokens in the right side o…
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter
Lijun Wu, Xu Tan, Di He +4
Neural machine translation usually adopts autoregressive models and suffers from exposure bias as well as the consequent error propagation problem. Many previous works have discuss…