综述:对话系统(未完成,不想写了,原文介绍太粗略--感兴趣自己看看也还是可以了解各种思路)
对话系统分类:
- 面向特定任务的系统
- 面向非特定任务的系统
面向特定任务(Task-oriented dialogue system)的对话系统的总体架构(pipeline)
NLU-> Dialogue state tracking -> Policy learning -> NLG
NLU: map natural language into semantic slots.
Two sorts of slots in NLU:
- utterance level representation: user’s intent or utterance category. This type slot filling is done by classification of intents or content categories.
- word level representation: NER etc. This information is attained by sequence labeling models such as CRF, etc.
Dialogue state tracking: slot filling for intent-recognition, or maintain a distribution over different goals.
Policy learning: Reinforcement learning or supervised learning. KB can be used to guide the conversation.
NLG: …
End2End: …