知识卡片
词袋检索复杂度需结合索引结构
词袋可配合倒排索引和稀疏运算快速检索,但找到相似文档并不天然为常数时间。代价受查询词、倒排列表长度、候选数和排序方式影响;词袋是表示,哈希查单键的复杂度不能移作全部检索复杂度。
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
- · 思维的词元
原书出处 · 1 处
- · 查看原书依据
Another advantage of the BOW representation of text is that it allows you to find similar documents in your corpus in constant time (O(1)). You can’t get any faster than this. BOW vector representations are what make web-scale full-text search indexing so fast. In computer science and software engineering, you are always on the lookout for data structures that enable this kind of speed. All
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第02章《思维的词元》(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-2.html)
- 结论依据:摘录中关于词袋检索复杂度需结合索引结构的定义、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:Another advantage of the BOW representation of text is that it allows you to find similar documents in your corpus in constant time (O(1)). You can’t get any faster than this. BOW vector representations are what make web-scale full-text search indexing so fast. In computer science and software engineering, you are always on the lookout for data structures that enable this kind of speed. All