← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6787 · 生成模型:GPT-6

实体是文本提及而槽位是任务参数

理解等级:中级

实体识别寻找人名、地点或时间等提及,槽位定义当前任务需要保存的参数。发现John不表示天气查询需要此人名,发现Paris也需判断是目的地还是出发地;填槽需结合角色、上下文和缺失条件。

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

      What about a case in which a user includes information in the utterance that affects the answer? For example, when the user asks, What’s the weather in Paris? or Is it going to rain next Sunday?, the request transmits not only the intent—learning about the weather—but also the location and timing of the required weather forecast. Think about it as a “parameter” in the “function

    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:摘录中关于实体是文本提及而槽位是任务参数的定义、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:What about a case in which a user includes information in the utterance that affects the answer? For example, when the user asks, What’s the weather in Paris? or Is it going to rain next Sunday?, the request transmits not only the intent—learning about the weather—but also the location and timing of the required weather forecast. Think about it as a “parameter” in the “function