知识卡片
共指链输出需要逐项回读原句
链中每个索引代表一处提及,可帮助将人物代词连到同一实体。但本章把revise it中的it连到advice,实际语境更支持前面的paper;看到链已生成不能直接宣称全部正确,错误合并会污染后续关系。
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
Your transformer-powered Coreferee pipeline was able to find two coreference chains that link mentions of entities together in two separate chains. In Python, a chain typically refers to a list of lists. Chains are used to store entities within Coreferee because each reference can potentially be represented with a list of tokens (an n-gram). The two chains in this sentence represent two distinct real-world objects:
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:摘录中关于共指链输出需要逐项回读原句的定义、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:Your transformer-powered Coreferee pipeline was able to find two coreference chains that link mentions of entities together in two separate chains. In Python, a chain typically refers to a list of lists. Chains are used to store entities within Coreferee because each reference can potentially be represented with a list of tokens (an n-gram). The two chains in this sentence represent two distinct real-world objects: