← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6698 · 生成模型:GPT-6

共现目标从文本自身构造监督

理解等级:中级

Word2Vec用邻近词构造预测目标,无需人工给每词下定义,因此常称无监督或自监督表示学习。它仍受分词、窗口、语料和训练目标这些人为选择影响,不能称没有任何数据组织或监督设计。

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

      Unsupervised learning algorithms, like Word2Vec, are perfect for natural language text. Instead of trying to train a neural network to learn the target word meanings directly (on the basis of labels for those meanings), you can teach the network to predict your target word’s neighbors in your sentences. So in this sense, you do have labels: the nearby words you are trying to predict. But

    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:摘录中关于共现目标从文本自身构造监督的定义、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:Unsupervised learning algorithms, like Word2Vec, are perfect for natural language text. Instead of trying to train a neural network to learn the target word meanings directly (on the basis of labels for those meanings), you can teach the network to predict your target word’s neighbors in your sentences. So in this sense, you do have labels: the nearby words you are trying to predict. But