知识卡片
命名实体不是所有名词的集合
人名常是PROPN,代词可指实体但不一定被NER标注为命名实体,日期也不只是名词。不能把NOUN当实体识别的充要条件;实体类别依标注方案,关系也不必都由单个动词表达。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
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
To trigger correct actions with natural language, you need something like an NLU pipeline or parser that is a little less fuzzy than a transformer or large language model. You need to know that me represents a particular kind of named entity: a person. Named entities are natural language terms, or n-grams, that refer to a particular thing in the real world, such as a
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:摘录中关于命名实体不是所有名词的集合的定义、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:To trigger correct actions with natural language, you need something like an NLU pipeline or parser that is a little less fuzzy than a transformer or large language model. You need to know that me represents a particular kind of named entity: a person. Named entities are natural language terms, or n-grams, that refer to a particular thing in the real world, such as a