ASCII is a character-encoding standard that assigns numeric codes to a limited set of Latin letters, digits, punctuation marks, and control characters. In multilingual text processing, converting text to pure ASCII—“asciifying” it—removes diacritics and typographic variations that could give a model irrelevant clues. section 8.2
For surname classification, asciifying O’Néàl as O'Neal and Çetin as Cetin helps a model learn spelling patterns rather than accents, cedillas, or curly punctuation. The resulting normalization supports broader generalization across Latin-script text, including transliterations. section 8.2
>>> from nlpia2.string_normalizers import Asciifier
>>> asciify = Asciifier()
>>> asciify("O’Néàl")
"O'Neal"
>>> asciify("Çetin")
'Cetin'
Run the Asciifier on names with diacritics and typographic punctuation to inspect their pure-ASCII forms. section 8.2
