activity
20192022
most citedLearning Deep Transformer Models for Machine Translation

97 citations · 117 across the 8 of their papers we have counts for

collaborators

9 papers

physics.acc-ph2022

A machine-learning based closed orbit feedback for the SSRF storage ring

Ruichun Li, Qinglei Zhang, Bocheng Jiang +4

In order to improve the stability of synchrotron radiation, we developed a new method of machine learning-based closed orbit feedback and piloted it in the storage ring of the Shan…

cs.CL2020

Layer-Wise Multi-View Learning for Neural Machine Translation

Qiang Wang, Changliang Li, Yue Zhang +2

Traditional neural machine translation is limited to the topmost encoder layer's context representation and cannot directly perceive the lower encoder layers. Existing solutions us…

cs.LG20201 cited

Learning Architectures from an Extended Search Space for Language Modeling

Yinqiao Li, Chi Hu, Yuhao Zhang +6

Neural architecture search (NAS) has advanced significantly in recent years but most NAS systems restrict search to learning architectures of a recurrent or convolutional cell. In…

cs.CL20201 cited

Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation

Bei Li, Hui Liu, Ziyang Wang +5

In encoder-decoder neural models, multiple encoders are in general used to represent the contextual information in addition to the individual sentence. In this paper, we investigat…

physics.acc-ph2020

Extreme bright coherent synchrotron radiation produced in a low emittance electron storage ring by the angular dispersion induced microbunching scheme

Changliang Li, Chao Feng, Bocheng Jiang

Generation of extreme bright coherent synchrotron radiation in a short wavelength range is of remarkable interest in the synchrotron light source community. In this paper, a novel…

cs.SD2020

Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks

Jingdong Li, Hui Zhang, Xueliang Zhang +1

In recent decades, neural network based methods have significantly improved the performace of speech enhancement. Most of them estimate time-frequency (T-F) representation of targe…