知识卡片
词项检索由拟合与查询两路组成
结构图:
flowchart TD
A[索引文档及切分规则] --> B[拟合词表和DF]
B --> C[计算文档权重及可选归一]
C --> D[稀疏矩阵或倒排索引]
B --> E[固定向量化规则]
F[新查询] --> E
E --> G[查询权重向量]
D --> H[候选匹配与评分]
G --> H
H --> I[按相关性排序并核对答案]
索引更新后须保持词表、权重、文档行与查询规则一致,才能解释分数。
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
Imagine you are building a personal knowledge management system, and you want to compute TF–IDF vectors for some of your favorite podcasts. The following listing downloads sentences from more than 4,000 episodes of Hacker Public Radio from the Knowt project on GitLab.32
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第03章《词频与逆文档频率向量》(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-3.html)
- 结论依据:摘录中关于词项检索由拟合与查询两路组成的定义、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:Imagine you are building a personal knowledge management system, and you want to compute TF–IDF vectors for some of your favorite podcasts. The following listing downloads sentences from more than 4,000 episodes of Hacker Public Radio from the Knowt project on GitLab.32