← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6655.d · 生成模型:GPT-6

词元切分和语言标注分开计时

理解等级:中级

spaCy全流水线还可能做词性、句法、词形还原和实体识别,不能把nlp(text)的总耗时直接当分词器自身速度。禁用不需模块可减少成本,但也会失去相应输出;比较工具应固定任务功能、文本、版本与硬件。

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

      You can see that spaCy does a lot more than simply separate text into tokens. It also identifies sentence boundaries to automatically segment your text into sentences, and it tags tokens with various attributes, like their POS and even their role within the syntax of a sentence. You can see the lemmas displayed by displaCy beneath the literal text for each token.5 Later in the

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第02章《思维的词元》(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-2.html) - 结论依据:摘录中关于词元切分和语言标注分开计时的定义、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:You can see that spaCy does a lot more than simply separate text into tokens. It also identifies sentence boundaries to automatically segment your text into sentences, and it tags tokens with various attributes, like their POS and even their role within the syntax of a sentence. You can see the lemmas displayed by displaCy beneath the literal text for each token.5 Later in the