Achieving Human Parity on Automatic Chinese to English News Translation
arXiv (Cornell University)Published 15 March 2018Open access
Hany Hassan, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan H. Clark, Christian Federmann
Citations578
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is found that Microsoft's 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.
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 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. 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.
Keywords
Computer Science
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)
50,318 Citations2021Mandi, Jayanta, Canoy, Rocsildes +2 more
A simple numeric simulation of DNA-co-polymerized hydrogel shape change and a genetic algorithm that generates and selects large batches of material designs that compete with one another to evolve and converge on optimal objective-matching designs are constructed.
NatureMastering the game of Go with deep neural networks and tree search
15,831 Citations2016David Silver, Aja Huang +18 more
Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.
arXiv (Cornell University)Sequence to Sequence Learning with Neural Networks
13,362 Citations2014Ilya Sutskever, Oriol Vinyals +1 more
arXiv (Cornell University)Deep Residual Learning for Image Recognition
4,720 Citations2015Kaiming He, Xiangyu Zhang +2 more
A Study of Translation Edit Rate with Targeted Human Annotation
2,402 Citations2006Matthew Snover, Bonnie J. Dorr +3 more
A new, intuitive measure for evaluating machine translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments is defined.
DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
2,105 Citations2017Zili Yi, Hao Zhang +2 more
A novel dual-GAN mechanism is developed, which enables image translators to be trained from two sets of unlabeled images from two domains, and can even achieve comparable or slightly better results than conditional GAN trained on fully labeled data.
Intelligent Selection of Language Model Training Data
539 Citations2010Robert C. Moore, William D. Lewis
This work addresses the problem of selecting non-domain-specific language model training data to build auxiliary language models for use in tasks such as machine translation by comparing the cross-entropy, according to domain-specific and non- domain-specifc language models, for each sentence of the text source used to produce the latter language model.
NPARCBatch Tuning Strategies for Statistical Machine Translation
338 Citations2012Colin Cherry, George Foster
It is found that a simple and efficient batch version of MIRA performs at least as well as training online, and consistently outperforms other options.
arXiv (Cornell University)Modeling Coverage for Neural Machine Translation
159 Citations2016Zhaopeng Tu, Zhengdong Lu +3 more
Natural Language EngineeringCan machine translation systems be evaluated by the crowd alone
146 Citations2015Yvette Graham, Timothy Baldwin +2 more
A new methodology for crowd-sourcing human assessments of translation quality is presented, which allows individual workers to develop their own individual assessment strategy and has a substantially increased ability to identify significant differences between translation systems.
Deep Dual Learning for Semantic Image Segmentation
104 Citations2017Ping Luo, Guangrun Wang +2 more
This work presents a novel learning setting, namely dual image segmentation (DIS), which consists of two complementary learning problems that are jointly solved, which outperforms an existing bestperforming baseline by 12.6% on Pascal VOC 2012 test set, without any post-processing such as CRF/MRF smoothing.
Proceedings of the AAAI Conference on Artificial IntelligenceDual Transfer Learning for Neural Machine Translation with Marginal Distribution Regularization
77 Citations2018Yijun Wang, Yingce Xia +5 more
This work leverages the dual translation model (target-to-source translation) to sample several mostly likely source-side sentences and avoid enumerating all possible candidate source sentences, and transfers the knowledge contained in the dual model to boost the training of the primal model (source- to-target translation), and calls this approach dual transfer learning.
HyTER: Meaning-Equivalent Semantics for Translation Evaluation
72 Citations2012Markus Dreyer, Daniel Marcu
An annotation tool is developed that enables us to create representations that compactly encode an exponential number of correct translations for a sentence, and it is shown that this metric provides better estimates of machine and human translation accuracy than alternative evaluation metrics.
International Conference on Computational LinguisticsImproving Attention Modeling with Implicit Distortion and Fertility for Machine Translation
33 Citations2016Shi Feng, Shujie Liu +4 more
Two novel models to improve attention-based neural machine translation are proposed, a recurrent attention mechanism as a implicit distortion model, and a fertility conditioned decoder as an implicit fertility model that significantly improve both the alignment and translation quality.
arXiv (Cornell University)Learning Residual Images for Face Attribute Manipulation
11 Citations2016Wei Shen, Rujie Liu