research
∙
11/07/2019
Microsoft Research Asia's Systems for WMT19
We Microsoft Research Asia made submissions to 11 language directions in...
share
research
∙
09/15/2019
Hint-Based Training for Non-Autoregressive Machine Translation
Due to the unparallelizable nature of the autoregressive factorization, ...
research
∙
07/03/2019
Depth Growing for Neural Machine Translation
While very deep neural networks have shown effectiveness for computer vi...
research
∙
02/22/2019
Non-Autoregressive Machine Translation with Auxiliary Regularization
As a new neural machine translation approach, Non-Autoregressive machine...
research
∙
10/29/2018
Learning to Teach with Dynamic Loss Functions
Teaching is critical to human society: it is with teaching that prospect...
research
∙
09/01/2018
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter
Neural machine translation usually adopts autoregressive models and suff...
research
∙
08/27/2018
A Study of Reinforcement Learning for Neural Machine Translation
Recent studies have shown that reinforcement learning (RL) is an effecti...
research
∙
08/22/2018
Neural Architecture Optimization
Automatic neural architecture design has shown its potential in discover...
research
∙
06/08/2018
Towards Binary-Valued Gates for Robust LSTM Training
Long Short-Term Memory (LSTM) is one of the most widely used recurrent s...
research
∙
05/09/2018
Learning to Teach
Teaching plays a very important role in our society, by spreading human ...
research
∙
03/15/2018
Achieving Human Parity on Automatic Chinese to English News Translation
Machine translation has made rapid advances in recent years. Millions of...
research
∙
04/20/2017
Adversarial Neural Machine Translation
In this paper, we study a new learning paradigm for Neural Machine Trans...
research
∙
02/28/2017
Learning What Data to Learn
Machine learning is essentially the sciences of playing with data. An ad...
research
∙
04/07/2016
Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves
We propose Sentence Level Recurrent Topic Model (SLRTM), a new topic mod...
research
∙
10/09/2014