GitHub - google/sentencepiece: Unsupervised text tokenizer for Neural Network-based text generation.

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

[nazoking]

よさそう

[nagayama]

“Unsupervised text tokenizer for Neural Network-based text generation. ”

[efcl]

言語に依存しない分かち書き

[braitom]

Language independentな分かち書き

[SWIMATH2]

強そう

[restartr]

"No pre-tokenization is required" "There is no language-dependent logic"

[dowhile]

カカシみたいなやつかな

[elu_18]

便利そう :thinking_face: https://t.co/jCyJRmthdy

[MichaeL]

ニューラルネットワークベースの言語非依存の分かち書き

[somemo]

“Purely data driven: SentencePiece trains tokenization and detokenization models from only raw sentences. No pre-tokenization (Moses tokenizer/MeCab/KyTea) is required. Language independent: ”

[quabbin]

ふ～む