[NLG] Zero-Shot Dialog Generation with Cross-Domain Latent Actions

时间 2021-01-16

标签 zero-shot dialogsystem generator 栏目 HTML 繁體版

原文原文链接

摘要：简单来说，就是实现了对话生成的zero shot(零次学习)。首先在一些source domain当中学习一些domain的基本描述，希望学到的这些基本描述能够用于target domain的对话生成，其中source domain的领域和target domain完全不一样。但是属性是共同的。主要工作： 1.提出来一种新的抽取domain 属性和描述的方法：seed re

>>阅读原文<<

1. [NLG] Domain Adaptive Dialog Generation via Meta Learning
2. [NLG] Pretraining for Conditional Generation with Pseudo Self Attention
3. [NLG]A Working Memory Model for Task-oriented Dialog Response Generation
4. [NLG]Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach
5. 论文笔记《Paraphrase generation with latent bag of words》
6. 对话系统中的NLG
7. Dialog without Buttons、Dialog with Buttons Bottom与Dialog with Buttons Right区别
8. 论文阅读-Structure-based Generation(SBG) System for E2E NLG Challenge
9. Neural Headline Generation with Minimum Risk Training
10. WebService Client Generation Error with JDK8
更多相关文章...
• XSLT 元素 - XSLT 教程
• ASP.NET MVC - 模型 - ASP.NET 教程
• IntelliJ IDEA 代码格式化配置和快捷键
• 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解

最新文章

1. 微软准备淘汰 SHA-1
2. Windows Server 2019 Update 2010，20H2
3. Jmeter+Selenium结合使用(完整篇)
4. windows服务基础
5. mysql 查看线程及kill线程
6. DevExpresss LookUpEdit详解
7. GitLab简单配置SSHKey与计算机建立连接
8. 桶排序(BucketSort)
9. 桶排序(BucketSort)
10. C++ 桶排序（BucketSort）

本站公众号

欢迎关注本站公众号,获取更多信息

1. [NLG] Domain Adaptive Dialog Generation via Meta Learning
2. [NLG] Pretraining for Conditional Generation with Pseudo Self Attention
3. [NLG]A Working Memory Model for Task-oriented Dialog Response Generation
4. [NLG]Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach
5. 论文笔记《Paraphrase generation with latent bag of words》
6. 对话系统中的NLG
7. Dialog without Buttons、Dialog with Buttons Bottom与Dialog with Buttons Right区别
8. 论文阅读-Structure-based Generation(SBG) System for E2E NLG Challenge
9. Neural Headline Generation with Minimum Risk Training
10. WebService Client Generation Error with JDK8

>>更多相关文章<<