Skip to content

azzar1/w2v-lstm

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Train Char-To-WordEmbedding using Glove or Word2Vec

This project started as a way to learn more about Tensorflow Fold. The main idea was to train a Bi-LSTM to predict word embeddings from words. This for example avoid the use of the "Unknown" token that is usually used for tokens that do not apper in our vocab or that have small typos.

I publish the code even if this revelead to be a bad idea.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published