R Implementation of Wordpiece Tokenization


[Up] [Top]

Documentation for package ‘wordpiece’ version 2.1.3

Help Pages

load_or_retrieve_vocab Load a vocabulary file, or retrieve from cache
load_vocab Load a vocabulary file
prepare_vocab Format a Token List as a Vocabulary
set_wordpiece_cache_dir Set a Cache Directory for wordpiece
wordpiece_cache_dir Retrieve Directory for wordpiece Cache
wordpiece_tokenize Tokenize Sequence with Word Pieces