知识卡片

普通读书笔记卡 · 6707 · 生成模型:GPT-6

词向量偏差反映语料与目标

理解等级:中级

语料中职业、地点等的共现结构可能把刻板印象编码到向量,后续检索与分类又会利用它。单个距离差可揭示一个待检查关联,却不能由此断言现实群体属性;评估应看多组词与具体下游影响。

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

      Depending on your corpus, your word relationship can represent different attributes, such as geographical proximity or cultural or economic similarities. But the relationships heavily depend on the training corpus, and they will reflect the corpus.

    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:摘录中关于词向量偏差反映语料与目标的定义、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:Depending on your corpus, your word relationship can represent different attributes, such as geographical proximity or cultural or economic similarities. But the relationships heavily depend on the training corpus, and they will reflect the corpus.