Adversarial Neural Machine Translation
来源:互联网 发布:简单优化模板源码下载 编辑:程序博客网 时间:2024/06/10 13:44
https://arxiv.org/abs/1704.06933
(Submitted on 20 Apr 2017)
In this paper, we study a new learning paradigm for Neural Machine Translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the translation given by a NMT model. To achieve this goal, inspired by the recent success of generative adversarial networks (GANs), we employ an adversarial training architecture and name it as Adversarial-NMT. In Adversarial-NMT, the training of the NMT model is assisted by an adversary, which is an elaborately designed Convolutional Neural Network (CNN). The goal of the adversary is to differentiate the translation result generated by the NMT model from that by human. The goal of the NMT model is to produce high quality translations so as to cheat the adversary. A policy gradient method is leveraged to co-train the NMT model and the adversary. Experimental results on English→ French and German→ English translation tasks show that Adversarial-NMT can achieve significantly better translation quality than several strong baselines.
Submission history
From: Fei Tian [view email][v1] Thu, 20 Apr 2017 05:08:47 GMT (210kb,D)
0 0
- Adversarial Neural Machine Translation
- Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
- Google's Neural Machine Translation System
- Neural Machine translation中的Attention机制
- Neural Machine Translation(NMT)技术概述
- Modeling Coverage for Neural Machine Translation
- Massive Exploration of Neural Machine Translation Architectures
- Towards String-to-Tree Neural Machine Translation
- 【nlp论文阅读】Adversal Neural Machine Translation
- A novel approach to neural machine translation
- 神经网络机器翻译Neural Machine Translation: Attention Mechanism
- Neural Machine Translation论文阅读笔记
- [ACL2017]Sequence-to-Dependency Neural Machine Translation
- 神经网络机器翻译Neural Machine Translation(1): Encoder-Decoder Architecture
- 神经网络机器翻译Neural Machine Translation(2): Attention Mechanism
- 神经网络机器翻译Neural Machine Translation(4): Modeling Coverage & MRT
- 神经网络机器翻译Neural Machine Translation(5): Gradient-based Optimization Algorithms
- 阅读小结:Google's Neural Machine Translation System
- 怎样学习最高效?
- 西邮Linux兴趣小组2017纳新免试题揭秘
- 解决Mysql中文乱码以及Incorrect string value的问题
- 4.2.3 修改表结构ALTER TABLE
- db2 导出表结构,导入表,分配权限,导出表数据,导入表数据
- Adversarial Neural Machine Translation
- WEB接口测试之Jmeter接口测试自动化 (三)(数据驱动测试) 接口测试与数据驱动
- JSP-EL表达式
- 前端MVC
- 关于Map集合的三种遍历方法
- 针对Excel表格文件操作的编程实现
- jdbc——事务
- 基于RNN的文本生成算法的代码运转
- Dagger2的使用与理解(1)