知识卡片
语义检索弥补词面不重合
查询和相关文档可能使用不同词,稠密表示可让部分语义相近文本成为候选。效果取决于嵌入训练与领域,否定、数字和细节仍会错;全文和语义检索可互补,不应因向量相似就把文档内容当答案。
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
Semantic search allows you to find what you are looking for, even when you aren’t sure of the exact words the authors used when they wrote a piece of text. Imagine you are searching for articles about big cats. If the corpus contains texts about several species, like jaguars, tigers, and lions, but never mentions the word cat, your search query won’t return any documents.
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第10章《真实世界中的大语言模型》(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-10.html)
- 结论依据:摘录中关于语义检索弥补词面不重合的定义、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:Semantic search allows you to find what you are looking for, even when you aren’t sure of the exact words the authors used when they wrote a piece of text. Imagine you are searching for articles about big cats. If the corpus contains texts about several species, like jaguars, tigers, and lions, but never mentions the word cat, your search query won’t return any documents.