Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
来源:互联网 发布:超轻粘土批发淘宝 编辑:程序博客网 时间:2024/05/22 14:33
https://arxiv.org/pdf/1703.04887
This paper proposes a new route for applying the generative adversarial nets (GANs) to NLP tasks (taking the neural machine translation as an instance) and the widespread perspective that GANs can't work well in the NLP area turns out to be unreasonable. In this work, we build a conditional sequence generative adversarial net which comprises of two adversarial sub models, a generative model (generator) which translates the source sentence into the target sentence as the traditional NMT models do and a discriminative model (discriminator) which discriminates the machine-translated target sentence from the human-translated sentence. From the perspective of Turing test, the proposed model is to generate the translation which is indistinguishable from the human-translated one. Experiments show that the proposed model achieves significant improvements than the traditional NMT model. In Chinese-English translation tasks, we obtain up to +2.0 BLEU points improvement. To the best of our knowledge, this is the first time that the quantitative results about the application of GANs in the traditional NLP task is reported. Meanwhile, we present detailed strategies for GAN training. In addition, We find that the discriminator of the proposed model shows great capability in data cleaning.
- Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
- 论文引介 | NMT with Conditional Sequence Generative Adversarial Nets
- Conditional Generative Adversarial Nets
- Adversarial Neural Machine Translation
- SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
- SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
- Conditional Generative Adversarial Nets论文笔记
- Conditional Generative Adversarial Nets论文翻译
- [生成对抗网络] 论文研读-SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
- Generative Adversarial Nets
- Generative Adversarial Nets
- GAN: Generative Adversarial Nets
- Generative Adversarial Nets
- Generative Adversarial Nets
- Triple Generative Adversarial Nets
- Generative Adversarial Nets
- 每日论文image-to-Image Translation with Conditional Adversarial Networks
- 《Image-to-Image Translation with Conditional Adversarial Networks》论文笔记
- Android的消息机制
- PHP 图片下载功能
- iMOOC学习笔记:Java的Excel读写操作入门实践-利用POI解析Excel文件(二)
- LVS安装使用详解
- Linux用户态和内核态通信
- Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
- NOR型闪存与NAND型闪存的区别
- 网易2017春招笔试真题编程题集合——2.优雅的点
- does not contain bitcode. You must rebuild it with
- http://toolbar.netcraft.com/site_report?url=www.google.cn
- PHP特性整合 php7特性
- weui.css中flex容器下子项目的水平和垂直居中
- 查看本地windows密码方法
- NanoPi—M1(H3)———编译Android内核,依赖编译后的内核编译内核模块