Deep-Learning-for-NLP

This repo contains code for:

1. Using the Word2Vec package from the Gensim library [https://radimrehurek.com/gensim/index.html] for producing word2vec embeddings on your own dataset
2. Using a bidirectional stacked RNN with LSTM cells for classifying whether a movie review of the IMDB dataset is positive or negative
3. Using a Convolutional Neural Network for classifying whether a movie review of the IMDB dataset is positive or negative
4. Using the Optuna framework for faster hyperparameter tuning of the above architectures ((2)(3))
5. Finetuning a pretrained model from HugginFace on the IMDB Dataset for classifying whether a movie review of the IMDB dataset is positive or negative. Here DistilBERT is used for computational efficiency.