On Sonntag 20 November 2005 16:48, Koji Sekiguchi wrote: > Could someone explain what "stemming" is?
Stemming usually means to cut off characters from the end of the word, e.g. walked -> walk, walking -> walk. However, this does not necessarily produce a real word, e.g. a stemmer could also change house and houses to "hous". Also, cutting of characters isn't enough for irregular words, e.g. you cannot get from "went" to "go" by just cutting of characters. A lemmatizer solves these problems, i.e. it always produces real words, even for irregular forms. It usually needs a table of irregular forms for this. Regards Daniel -- http://www.danielnaber.de --------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
