知识卡片
关系抽取需处理不止简单主谓宾
nsubj与dobj可支持一部分主动句,遇到被动、并列、介词、否定或跨句时需额外规则。先明确目标关系与角色定义,再由句法候选到语义验证;句内出现动词不意味着已找到现实中成立的边。
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
The simplest way to extract relations out of the text is to look for all subject–verb–object triplets using the nsubj and dobj tags of the ROOT word. But let’s do something a bit more complex. What if you want to extract information about meetings between historical figures from Wikipedia? You can use the spaCy package in two different ways to match these patterns in O(1)
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:摘录中关于关系抽取需处理不止简单主谓宾的定义、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:The simplest way to extract relations out of the text is to look for all subject–verb–object triplets using the nsubj and dobj tags of the ROOT word. But let’s do something a bit more complex. What if you want to extract information about meetings between historical figures from Wikipedia? You can use the spaCy package in two different ways to match these patterns in O(1)