Documentation

Up and running in under a minute

Cleaning up the Text for you.

A class to process the textual data.

Method to perform tokenization on sentences.

Method to perform stemming on words.

Method to perform stopword removal on list of words.

A class to perform word embedding.

Method to get embedding vector for word.

Method to get closely related words.

Method to transliterate word from one script to another.

Method to transliterate word back to the original script.

PyTorch Attention module part of torch.nn

PyTorch Attention module part of torch.nn

Method to download and load corpora and datasets.