Paper Info
Title
Achieving Human Parity on Automatic Chinese to English News Translation.
Abstract
Machine translation has made rapid advances in recent years. Millions of people are using it today in online translation systems and mobile applications in order to communicate across language barriers. The question naturally arises whether such systems can approach or achieve parity with human translations. In this paper, we first address the problem of how to define and accurately measure human parity in translation. We then describe Microsoftu0027s machine translation system and measure the quality of its translations on the widely used WMT 2017 news translation task from Chinese to English. We find that our latest neural machine translation system has reached a new state-of-the-art, and that the translation quality is at human parity when compared to professional human translations. We also find that it significantly exceeds the quality of crowd-sourced non-professional translations.
Year
Venue
Field
2018
arXiv: Computation and Language
Language barrier,Computer science,Machine translation system,Machine translation,Artificial intelligence,Natural language processing,Parity (mathematics)
DocType
Volume
Citations 
Journal
abs/1803.05567
26
PageRank 
References 
Authors
0.79
9
24
Name
Order
Citations
PageRank
Hany Hassan1522.30
Anthony Aue229016.87
Chang Chen3417.11
Vishal Chowdhary41757.80
Jonathan H. Clark541116.42
Christian Federmann626227.49
Xuedong Huang71390283.19
Marcin Junczys-Dowmunt831224.24
William D. Lewis917118.53
Mu Li1095866.10
Shujie Liu1133837.84
Tie-yan Liu124662256.32
Renqian Luo13283.58
Arul Menezes14261.47
Tao Qin152384147.25
frank seide161489101.15
Xu Tan178823.94
Fei Tian1816011.88
Lijun Wu1912421.21
Shuangzhi Wu205310.37
Yingce Xia2113019.23
Dongdong Zhang22261.81
Zhirui Zhang23438.12
Ming Zhou244262251.74