知识卡片
静态坐标不天然对应可命名属性
原始嵌入维度通常是分布式的,并非一个坐标专管地点或人物。nessvector一类属性分数需另外选方向、参照词或组合规则,属于派生测量;名字可解释不代表已客观测出词义或现实人物的属性。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 用词嵌入推理
原书出处 · 1 处
- · 查看原书依据
A helpful mental model for understanding word vectors is thinking of word vectors as a list of weights or scores. Each weight or score is associated with a specific dimension of meaning for that word, as demonstrated in the following listing.
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:摘录中关于静态坐标不天然对应可命名属性的定义、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:A helpful mental model for understanding word vectors is thinking of word vectors as a list of weights or scores. Each weight or score is associated with a specific dimension of meaning for that word, as demonstrated in the following listing.