February 2018
Intermediate to advanced
378 pages
10h 14m
English
This is a more advanced approach than stemming. Instead of reducing words to stems, lemmatizers match every word to its lemma, the form in a dictionary. This is especially useful for languages such as Polish, where one verb can easily have 220 different grammatical forms, mostly with different spellings: http://wsjp.pl/do_druku.php?id_hasla=34745&id_znaczenia=0.
The problem here is homonyms.
Read now
Unlock full access