1.

Does the vocabulary of a corpus remain the same before and after text normalization? Why?

Answer»

No, the vocabulary of a corpus does not remain the same before and after text normalization. 

Reasons are:

● In normalization the text is normalized through various steps and is lowered to minimum vocabulary since the machine does not require grammatically correct statements but the essence of it. 

● In normalization Stop words, Special Characters and Numbers are removed. 

● In stemming the affixes of words are removed and the words are converted to their base form.

So, after normalization, we get the reduced vocabulary.



Discussion

No Comment Found