November 2018
Beginner to intermediate
182 pages
4h 48m
English
While checking for stop words, spaCy did not automatically lowercase our input. On the other hand, lemmatization does this for us. It converted "Apple" to "apple" and "Banana" to "banana".
This is one of the ways spaCy makes our lives easier, though slightly inconsistent. While removing stop words, we want to preserve THE in "THE ADVENTURES OF SHERLOCK HOLMES" while removing the in "the street was black". The opposite is usually true in lemmatization; we care more about how the word was used in context and use a proper lemma accordingly.
Read now
Unlock full access