Jindřich questions

Jindřich answers

• How do I translate using HuggingFace from Chinese to English?
• BERT sentence embeddings from transformers
• Text normalization : Text similarity in Python. How to normalize Text spelling mismatch?
• How to get the probability of a particular token(word) in a sentence given the context
• Do I need to pre-tokenize the text first before using HuggingFace's RobertaTokenizer? (Different undersanding)
• How to find singular in the plural when some letters change? What is the best approach?
• How to add more features in multi text classification?
• How does Beam Search operate on the output of The Transformer?
• Fine-tune Bert for specific domain (unsupervised)
• How are the TokenEmbeddings in BERT created?