Login / Signup
SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing.
Taku Kudo
John Richardson
Published in:
CoRR (2018)
Keyphrases
</>
language independent
text processing
n gram
natural language processing
machine translation
text classification
text mining
cross lingual
information extraction
co occurrence
field of natural language processing
text retrieval
machine learning
language specific
language model
part of speech
word level