← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6697.b · 生成模型:GPT-6

变形差向量只在部分规律上近似

理解等级:中级

复数与单数向量的差可在若干词对间呈相似方向,支持类比实验。但词义、词频和不规则形式会影响偏移,coffee与coffees等也可能有用法差异;不能将一个差向量当所有语言所有名词统一复数规则。

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 research team also discovered that the difference between a singular and a plural word is often roughly the same magnitude and in the same direction. You can see how to compute this pluralization vector in equation 6.2.

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第06章《用词嵌入推理》(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-6.html) - 结论依据:摘录中关于变形差向量只在部分规律上近似的定义、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 research team also discovered that the difference between a singular and a plural word is often roughly the same magnitude and in the same direction. You can see how to compute this pluralization vector in equation 6.2.