Bert Model wrapper with TensorFlow Wrapper
Id of sentence start Token
Id of sentence end Token.
Configuration for TensorFlow session
labels which model was trained with in order
TF v2 signatures in Spark NLP
Encode the input sequence to indexes IDs adding padding where necessary
Encode the input sequence to indexes IDs adding padding where necessary
Id of sentence end Token.
Id of sentence end Token.
Id of sentence start Token
Id of sentence start Token
Bert Model wrapper with TensorFlow Wrapper
Word-level and span-level alignment with Tokenizer https://github.com/google-research/bert#tokenization
Word-level and span-level alignment with Tokenizer https://github.com/google-research/bert#tokenization
### Input orig_tokens = ["John", "Johanson", "'s", "house"] labels = ["NNP", "NNP", "POS", "NN"]
# bert_tokens == ["[CLS]", "john", "johan", "##son", "'", "s", "house", "[SEP]"] # orig_to_tok_map == [1, 2, 4, 6]