Stephan Tulkens

Results 4 repositories owned by Stephan Tulkens

piecelearn

19
Stars
1
Forks
Watchers

Learning BPE embeddings by first learning a segmentation model and then training word2vec

reach

22
Stars
4
Forks
Watchers

Load embeddings and featurize your sentences.

somber

52
Stars
13
Forks
Watchers

Recursive Self-Organizing Map/Neural Gas.

unitoken

21
Stars
1
Forks
Watchers

Tokenization across languages. Useful as preprocessing for subword tokenization.