Implementations of various NLP models using Python
This is an ongoing research. It builds on using the classic word embeddings used for Natural Language Processing (NLP) and moves to more complex models that make the use Deep Learning.
So far we have researched and demonsrated:
- How to create word embeddings (Word2vec, Glove)
- How to use these word embeddings to perform classification (by using Logistic Regression, SVM, MLP)
- How custom models differ from pre-trained NLP models
Most of the experiments are performed on a simple benchmark dataset (IMDB review dataset) for Sentiment Classification.
If github is unable to render a Jupyter notebook, copy the link of the notebook and enter into the nbviewer: https://nbviewer.jupyter.org/