知识卡片
模糊正则放宽形式匹配而非理解
允许有限次数插入、删除和替换,可让规则接受近似拼写,但需设置误差范围并处理多个近似候选。它降低某些格式脆弱性,也会引入误报;近似语法匹配仍不是对句义和用户意图的完整理解。
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
Will is an open source Python chatbot framework by Steven Skoczen with a completely different approach.59 Will can only be trained to respond to statements by programming it with regular expressions—a labor-intensive and data-light approach to NLP. This grammar-based approach is especially effective for question-answering systems and task-execution assistant bots, like Lex, Siri, and Google Now. These kinds of systems overcome the “brittleness” of regular
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第01章《会读写的机器与自然语言处理》(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-1.html)
- 结论依据:摘录中关于模糊正则放宽形式匹配而非理解的定义、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:Will is an open source Python chatbot framework by Steven Skoczen with a completely different approach.59 Will can only be trained to respond to statements by programming it with regular expressions—a labor-intensive and data-light approach to NLP. This grammar-based approach is especially effective for question-answering systems and task-execution assistant bots, like Lex, Siri, and Google Now. These kinds of systems overcome the “brittleness” of regular