NLP for Odia
This repository contains State of the Art Language models and Classifier for Odia, which is spoken in the Indian state of Odisha.
The models trained here have been used in Natural Language Toolkit for Indic Languages (iNLTK)
Dataset
Created as part of this project
Results
Language Model Perplexity
Architecture/Dataset | Odia Wikipedia Articles |
---|---|
ULMFiT | 26.57 |
TransformerXL | 26.81 |
Classification Metrics
ULMFiT
Dataset | Accuracy | Kappa Score |
---|---|---|
Odia News Dataset | 95.52 | 93.02 |
Visualizations
Embedding Space
Architecture | Visualization |
---|---|
ULMFiT | Embeddings projection |
TransformerXL | Embeddings projection |
Pretrained Language Model
Download pretrained Language Model from here
Classifier
Download classifier from here
Tokenizer
Trained tokenizer using Google's sentencepiece
Download the trained model and vocabulary from here