Skip to content

Python-based KNIME node implementing Word2Vec algorithms with Tensorflow

License

Notifications You must be signed in to change notification settings

sim2000dg/Word2VecPyNodeTF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

60 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Word2Vec Python-based KNIME node with Tensorflow

This KNIME extension contains a Python-based node which performs Word2Vec with both skip-gram and CBOW algorithms, letting the user choose between hierarchical softmax and negative sampling as approaches to perform the actual fit. The underlying engine for the fit and for some of the pre-processing is Tensorflow.

Some of the overall ideas for this implementation come from this great blog post/README file: https://github.com/chao-ji/tf-word2vec/blob/master/README.md