ngram 的哈希值:文档指纹识别
我正在尝试在 R 中实现文档指纹识别的筛选算法。
这里参考 http://www.ida.liu.se/~TDDC03/oldprojects/2005/final-projects/prj10.pdf
我的问题:
如何获得n-gram 的哈希值以及如何选择它们
nGrams <- c("adoru", "dorun", "orunr", "runru", "unrun", "nrunr" ,"runru",
"unrun","nruna", "runad", "unado", "nador", "adoru", "dorun", "orunr" ,"runru" ,
"unrun")
I am trying to implement the winnowing algorithm for document fingerprinting in R.
Here the reference http://www.ida.liu.se/~TDDC03/oldprojects/2005/final-projects/prj10.pdf
My question:
how do I get hashes of n-gram and how do I select those
nGrams <- c("adoru", "dorun", "orunr", "runru", "unrun", "nrunr" ,"runru",
"unrun","nruna", "runad", "unado", "nador", "adoru", "dorun", "orunr" ,"runru" ,
"unrun")
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论
评论(1)
看来这
将是一个好的开始。 (CRC32 始终为奇数,因此需要减 1。)
It seems as though
would be a good start. (CRC32 is always odd, so subtracting 1 is necessary.)