← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6654.a · 生成模型:GPT-6

词袋保留计数但丢掉全局词序

理解等级:中级

将词项分配到固定槽并计数,得到每个文档的词袋向量。相同词的不同排列会有相同表示,因而难区分论元顺序、否定范围和逻辑组合;词袋可作主题或检索基线,但不能说已保存全部意义或唯一恢复原句。

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

      But let’s think for a moment about what information has been lost in our effort to count all the words in the messages we receive. We assign the words to bins and store them away as bit vectors like a coin or token sorter (see figure 1.5) directing different kinds of tokens to one side or the other in a cascade of decisions that piles

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第01章《会读写的机器与自然语言处理》(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-1.html) - 结论依据:摘录中关于词袋保留计数但丢掉全局词序的定义、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:But let’s think for a moment about what information has been lost in our effort to count all the words in the messages we receive. We assign the words to bins and store them away as bit vectors like a coin or token sorter (see figure 1.5) directing different kinds of tokens to one side or the other in a cascade of decisions that piles