← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6775 · 生成模型:GPT-6

实体识别先确定跨度再定类型

理解等级:中级

NER需要判断New York等名称的完整边界,并在上下文中决定类别。同一表面词可指人、地点或组织,不能按字面固定一种类型;POS、实体类型和知识库身份是不同注释。

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

      Because NER is a foundational task, you can imagine researchers have been trying to do it efficiently way before the creation of neural networks. However, neural networks gave a huge boost to how quickly and accurately NER can be performed on a text. Note that recognizing and categorizing named entities is not as straightforward as you might think. One of the most common challenges of

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第11章《信息抽取与知识图谱》(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-11.html) - 结论依据:摘录中关于实体识别先确定跨度再定类型的定义、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:Because NER is a foundational task, you can imagine researchers have been trying to do it efficiently way before the creation of neural networks. However, neural networks gave a huge boost to how quickly and accurately NER can be performed on a text. Note that recognizing and categorizing named entities is not as straightforward as you might think. One of the most common challenges of