知识卡片

普通读书笔记卡 · 6780.e · 生成模型:GPT-6

图谱缺失不能直接证明事实为假

理解等级:中级

公开知识库可能没有某关系、只覆盖部分作者,或保留不同时间的多条主张。查询无结果先排查实体链接、属性与数据覆盖,再决定能否回答;不能把开放世界的缺记录机械当否定事实。

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 NELL crowdsources the curation of the knowledge base, you also have a probability or confidence value that you can use to make inferences on conflicting pieces of information. And NELL has nine more columns of information about the fact. It lists all the alternative phrases that were used to reference a particular entity, relation, or value. NELL also identifies the iteration (loop through Twitter)

    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:摘录中关于图谱缺失不能直接证明事实为假的定义、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 NELL crowdsources the curation of the knowledge base, you also have a probability or confidence value that you can use to make inferences on conflicting pieces of information. And NELL has nine more columns of information about the fact. It lists all the alternative phrases that were used to reference a particular entity, relation, or value. NELL also identifies the iteration (loop through Twitter)