trained data visualization

[fathimakmurshida]

could you please explain how to visualise the trained datset using tensorflow tsne in 2D and how you could calculate the similarity between words?

[kamalkraj]

The Vakku2vec repo contains Language Model and News Classifier. Language Model representation cannot be visualized directly.

But we have normal embeddings like GloVe on Malayalam which can be downloaded from here ( https://www.dropbox.com/s/kgwr9ye32r8jzsg/malayalam200.txt)

This medium blog (https://towardsdatascience.com/google-news-and-leo-tolstoy-visualizing-word2vec-word-embeddings-with-t-sne-11558d8bd4d) contains information on how to train a Word2Vec model and visualize using t-sne. You could skip the training part. And directly go for visualization.