知识卡片
字符三元组提供拼写近似线索
将规范化文本分成连续三字符片段,可依据重叠检索拼写近似词。边界处理必须在索引和查询一致,不同实现可采用不同补空白策略;它解决部分字面差异,不自动理解否定和同义,也不保证精确召回同时提高。
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
The inverted indices you learned about in the previous section are very useful for finding word matches but not for finding approximate matches of meaning or intent. Stemming and lemmatization can help increase the matching of different forms of the same word; however, what happens when your search contains typos or misspellings?
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:摘录中关于字符三元组提供拼写近似线索的定义、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:The inverted indices you learned about in the previous section are very useful for finding word matches but not for finding approximate matches of meaning or intent. Stemming and lemmatization can help increase the matching of different forms of the same word; however, what happens when your search contains typos or misspellings?