NLP for Kannada
August 6, 2020 ยท View on GitHub
This repository contains State of the Art Language models and Classifier for Kannada, which is spoken predominantly by Kannada people in India, mainly in the state of Karnataka.
The models trained here have been used in Natural Language Toolkit for Indic Languages (iNLTK)
Dataset
Created as part of this project
Open Source Datasets
Results
Language Model Perplexity (on validation set)
| Architecture/Dataset | Kannada Wikipedia Articles |
|---|---|
| ULMFiT | 70.10 |
| TransformerXL | 61.97 |
Classification Metrics
ULMFiT
| Dataset | Accuracy | MCC | Notebook to Reproduce results |
|---|---|---|---|
| IndicNLP News Article Classification Dataset - Kannada | 98.87 | 98.30 | Link |
Visualizations
Word Embeddings
| Architecture | Visualization |
|---|---|
| ULMFiT | Embeddings projection |
| TransformerXL | Embeddings projection |
Pretrained Models
Language Models
Download pretrained Language Model from here
Tokenizer
Trained tokenizer using Google's sentencepiece
Download the trained model and vocabulary from here