知识卡片

普通读书笔记卡 · 6705 · 生成模型:GPT-6

子词嵌入按字符片段组合词表示

理解等级:中级

fastText为词内字符n-gram学习表示,再组合来表达词并用于邻词预测。关键是利用子词组成输入词表示,而非简单把预测目标全部改成周围字符片段;边界标记、长度范围与实现规则共同决定片段集合。

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

      Researchers from Facebook took the concept of Word2Vec one step further45 by adding a new twist to model training. The new algorithm, which they named fastText, predicts the surrounding n-character grams, rather than just the surrounding words, like Word2Vec does. For example, the word whisper would generate the following 2- and 3-character grams:

    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:摘录中关于子词嵌入按字符片段组合词表示的定义、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:Researchers from Facebook took the concept of Word2Vec one step further45 by adding a new twist to model training. The new algorithm, which they named fastText, predicts the surrounding n-character grams, rather than just the surrounding words, like Word2Vec does. For example, the word whisper would generate the following 2- and 3-character grams: