Perform a Sentiment analysis using BERT on IMDB Movie Ratings Dataset.

IMDB dataset having 50K movie reviews for natural language processing or Text analytics.This is a dataset for binary sentiment classification containing substantially more data than previous benchmark datasets. The Dataset provides a set of 25,000 highly polar movie reviews for training and 25,000 for testing. So, predict the number of positive and negative reviews using either classification or deep learning algorithms.

• Dataset can be found here

BERT (Bidirectional Encoder Representations from Transformers) is a recent paper published by researchers at Google AI Language. It has caused a stir in the Machine Learning community by presenting state-of-the-art results in a wide variety of NLP tasks, including Question Answering (SQuAD v1.1), Natural Language Inference (MNLI), and others.

• For More about BERT click here

• First of all create a virtual environment and run requirements.txt file

• For model training download the BERT_BASE_UNCASED model from here.
• You can also refer to the official hugginface documentation for BERT from here.
• After downloading extract the zip file under ..src/input folder.
• Go to the ..src/training/config.py to check the configurations and dataset and the model path and change accordingly.
• After following the above steps navigate to ..src/training/ and run the app.py to begin training.
• After training is completed the weights of the model will be saved as per the name and location given in the config file.