Documentation
Quick Start
Up and running in under a minute
Preprocessing
Cleaning up the Text for you.
TextNormalizer
A class to process the textual data.
Tokenizer - Method
Method to perform tokenization on sentences.
Stem - Method
Method to perform stemming on words.
Remove Stop Words - Method
Method to perform stopword removal on list of words.
Embedding
A class to perform word embedding.
Get Vector - Method
Method to get embedding vector for word.
Get Closest - Method
Method to get closely related words.
Convert - Method
Method to transliterate word from one script to another.
Revert - Method
Method to transliterate word back to the original script.
BahdanauAttention
PyTorch Attention module part of torch.nn
LuongAttention
PyTorch Attention module part of torch.nn
Load Dataset - Method
Method to download and load corpora and datasets.