NLP for Punjabi

This repository contains State of the Art Language models and Classifier for Punjabi language (spoken in Indian sub-continent)

The models trained here have been used in Natural Language Toolkit for Indic Languages (iNLTK)

Dataset

Created as part of this project

1. Punjabi Wikipedia Articles

2. Punjabi News Dataset

Open Source Datasets

1. IndicNLP News Article Classification Dataset - Punjabi

Results

Language Model Perplexity (on validation set)

Architecture/Dataset	Punjabi Wikipedia Articles
ULMFiT	24.40
TransformerXL	14.03

Classification Metrics

ULMFiT

Dataset	Accuracy	MCC	Notebook to Reproduce results
IndicNLP News Article Classification Dataset - Punjabi	97.12	96.17	Link

Visualizations

Word Embeddings

Architecture	Visualization
ULMFiT	Embeddings projection
TransformerXL	Embeddings projection

Sentence Embeddings

Architecture	Visualization
ULMFiT	Encodings projection

Pretrained Models

Language Models

Download pretrained Language Models from here

Tokenizer

Unsupervised training using Google's sentencepiece

Download the trained model and vocabulary from here