Yingce Xia

Publications
Influence

Di He, Yingce Xia, +4 authors W. Ma
Computer Science
NIPS
1 November 2016

We develop a dual-learning mechanism, which can enable an NMT system to automatically learn from unlabeled data through a dual learning game. Expand

Deliberation Networks: Sequence Generation Beyond One-Pass Decoding

Yingce Xia, Fei Tian, +4 authors T. Liu
Computer Science
NIPS
4 December 2017

This work was done when Yingce Xia, Lijun Wu and Jianxin Lin were interns at Microsoft Research. Expand

Incorporating BERT into Neural Machine Translation

Jinhua Zhu, Yingce Xia, +5 authors T. Liu
Computer Science
ICLR
17 February 2020

We propose a new algorithm named BERT-fused model, in which we first use BERT to extract representations for an input sequence, and then the representations are fused with each layer of the encoder and decoder of the NMT model through attention mechanisms. Expand

Adversarial Neural Machine Translation

Lijun Wu, Yingce Xia, +4 authors T. Liu
Computer Science, Mathematics
ACML
1 April 2017

We study a new learning paradigm for Neural Machine Translation (NMT). Expand

Achieving Human Parity on Automatic Chinese to English News Translation

Hany Hassan, Anthony Aue, +21 authors M. Zhou
Computer Science
ArXiv
15 March 2018

We describe Microsoft's machine translation system and measure the quality of its translations on the widely used WMT 2017 news translation task from Chinese to English. Expand

Dual Supervised Learning

Yingce Xia, T. Qin, Wei Chen, Jiang Bian, N. Yu, T. Liu
Computer Science, Mathematics
ICML
3 July 2017

We propose training the models of two dual tasks simultaneously, and explicitly exploiting the probabilistic correlation between them to regularize the training process. Expand

Depth Growing for Neural Machine Translation

Lijun Wu, Yiren Wang, +5 authors T. Liu
Computer Science
ACL
3 July 2019

In this work, we propose an effective two-stage approach with three specially designed components to construct deeper NMT models, which result in significant improvements over the strong Transformer baselines on WMT$. Expand

Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation

Tianyu He, X. Tan, +4 authors T. Liu
Computer Science
NeurIPS
2018

We propose layer-wise coordination for NMT, which explicitly coordinates the learning of hidden representations of the encoder and decoder together layer by layer, gradually from low level to high level. Expand

Conditional Image-to-Image Translation

Jianxin Lin, Yingce Xia, T. Qin, Zhibo Chen, T. Liu
Computer Science
IEEE/CVF Conference on Computer Vision and…
1 May 2018

In this paper, we study a new problem, conditional image-to-image translation, which is to translate an image from the source domain to the target domain conditioned on a given image in the target. Expand

Budgeted Multi-Armed Bandits with Multiple Plays

Yingce Xia, T. Qin, Weidong Ma, N. Yu, T. Liu
Mathematics, Computer Science
IJCAI
9 July 2016

We study the multi-play budgeted multi-armed bandits (MP-BMAB) problem, in which pulling an arm receives both a random reward and a random cost, and a player pulls L(≥ 1) arms at each round. Expand

Recommended Authors