Closed soutsios closed 2 years ago
Is there really a need to Pre-process text (Deaccent - Lower) as described in https://github.com/nlpaueb/greek-bert#pre-process-text-deaccent---lower since its already something that bert tokenizer does (https://github.com/google-research/bert#tokenization) ?
No it's not. The tokenizer does it automatically. Sorry for the belated response...
Is there really a need to Pre-process text (Deaccent - Lower) as described in https://github.com/nlpaueb/greek-bert#pre-process-text-deaccent---lower since its already something that bert tokenizer does (https://github.com/google-research/bert#tokenization) ?