-
In this project I trained Hindi Language Model with BBC Hindi News Dataset and then Built a Hindi News Classifier.
-
Architecture : AWD-LSTM
-
Learn more about AWD-LSTM Here ---> ASGD Weight-Dropped LSTM
-
LSTM cell structure
- Model Summary :
- DataBlock :
- Used Mixed Precision training to decrease up the training time.
Achieved a final accuracy of 30% for the Hindi Language Model
-
Hindi News Dataset :
-
Classifier Data Block
-
News categories
-
'business' , 'china' , 'entertainment' , 'india' , 'institutional' , 'international' , 'learningenglish'
-
'multimedia' , 'news' , 'pakistan' , 'science' , 'social' , 'southasia' , 'sport'
-
Metrics I choose for the News dataset was a f1_score
average = macro
- Because there was a class imbalance in the news dataset
- **Top losses : **
Python v3.6.x
fastai v1
Numpy
Pandas
tqdm (Progress bar)
Jupyter Notebook (Visualisations)
- Practical Deep Learning for Coders MOOC by team fast.ai