No, the vocabulary of a corpus does not remain the same before and after text normalization. Reasons are –
1. 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.
2. In normalization Stop words, Special Characters, and Numbers are removed
3. In stemming the affixes of words are removed and the words are converted to their base form.
4. So, after normalization, we get a reduced vocabulary.
Study more about Natural Language Processing at Natural Language Processing Class 10