← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6697.d · 生成模型:GPT-6

单词与短语必须采用同一词表规则

理解等级:中级

预训练模型可能把多词短语用下划线连接,因此Marie_Curie与两个分开的词未必有相同键和向量。名称大小写、分词和短语合并都影响查找;将结果拼成字符串不代表模型已具有该短语的原始表示。

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

      Notice that compound words and common n-grams are joined together with an underscore character (“_”). Also notice that the value in the key-value mapping is a gensim.Vocab object that contains not only the index location for a word, so you can retrieve the Word2Vec vector, but also the number of times it occurred in the Google News 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:摘录中关于单词与短语必须采用同一词表规则的定义、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:Notice that compound words and common n-grams are joined together with an underscore character (“_”). Also notice that the value in the key-value mapping is a gensim.Vocab object that contains not only the index location for a word, so you can retrieve the Word2Vec vector, but also the number of times it occurred in the Google News corpus.