知识卡片
两算法一致率不是准确率
比较两个系统在相同输入上的断句是否一致,可定位分歧,不能判断谁正确,也不能把一致率当相对金标准的准确率。本例输出0.76而正文写93%,数字也未对齐,应回到实际实验与人工标注。
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
That is a significant time saver—2.3 versus 16 seconds on an eight-core i7 laptop. The statistical sentence segmenter is about five times faster than the full spaCy pipeline. The regular expression approach will still be much faster, but the statistical sentence segmenter will be more accurate. You can estimate the accuracy of these two algorithms by comparing the lists of sentences to see if they
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:摘录中关于两算法一致率不是准确率的定义、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:That is a significant time saver—2.3 versus 16 seconds on an eight-core i7 laptop. The statistical sentence segmenter is about five times faster than the full spaCy pipeline. The regular expression approach will still be much faster, but the statistical sentence segmenter will be more accurate. You can estimate the accuracy of these two algorithms by comparing the lists of sentences to see if they