← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6790.a · 生成模型:GPT-6

意图样例和会话策略是两类数据

理解等级:中级

Rasa的NLU样例用于学习意图和实体,domain定义可用对象及回复,stories描述会话序列,config控制处理组件。更换话术不自动训练新意图;一个顺利故事也不覆盖拒绝、未知角色和中途退出。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      The directory we are most interested in is the data directory. It contains the files that define the data used to train the chatbot’s NLU model. First, there’s the nlu.yml file, which contains the intents and examples of user utterances used to train the intent recognition model. So let’s start creating the intents used in our dialog. For every intent you want to define, you

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第12章《对话引擎与会话设计》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-12.html) - 结论依据:摘录中关于意图样例和会话策略是两类数据的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:The directory we are most interested in is the data directory. It contains the files that define the data used to train the chatbot’s NLU model. First, there’s the nlu.yml file, which contains the intents and examples of user utterances used to train the intent recognition model. So let’s start creating the intents used in our dialog. For every intent you want to define, you