dialog system resources
1.看哪些paper，可以从ACL2018这篇综述的第4章找 Neural Approaches to Conversational AI 2.对话管理比较有名的开源规则系统有
- RavenClaw: The RavenClaw dialog management framework: Architecture and systems
- TCP: Task Completion Platform: A self-serve multi-domain goal oriented dialogue platform
3.神经网络重点看的是剑桥实验室的工作，他们放出个开源的对话框架叫pydial(http://www.camdial.org/pydial)，几篇比较有名的论文和代码：
- NBT
- 项目地址: https://github.com/nmrksic/neural-belief-tracker
- 对应论文: Fully Data-Driven version of the Neural Belief Tracking (NBT) model
- Multi-domain NBT
- 项目地址: https://github.com/osmanio2/multi-domain-belief-tracking
- 对应论文: Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing
- Multi-WOZ
- 项目地址: https://github.com/budzianowski/multiwoz
- 对应论文: MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
- NNDial
- 项目地址: https://github.com/shawnwun/NNDIAL
- 对应论文: A Network-based End-to-End Trainable Task-oriented Dialogue System
- RNNLG
- 项目地址: https://github.com/shawnwun/RNNLG
- 对应论文: Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems