知识卡片
共指可视化必须保持词元位置
把索引显示在原token上方,并保留空白和句界,可以人工核对链条。字符宽度换行可能把索引或词切开,显示位置不等于模型token编号;应保存稳定索引与原文映射,方便定位多词提及。
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 make it easier to reason about these entities in your text, you will probably need some helper functions to visualize the coreference chains. At first, you can probably get away with displaying the token index numbers as headers above each sentence:
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:摘录中关于共指可视化必须保持词元位置的定义、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 make it easier to reason about these entities in your text, you will probably need some helper functions to visualize the coreference chains. At first, you can probably get away with displaying the token index numbers as headers above each sentence: