- This repository contains tutorials that cover different NLP applications leveraging Neural Network models. Currently 1 tutorial notebook is available in this repository:
nlp_classfication_lstm.ipynb
nlp_classfication_lstm.ipynb
- This notebook covers how to classify text data using an
LSTM
model build inTensorflow
framework. - Dataset used for analysis is the Clickbait Dataset taken from Kaggle website.
- Two different binary classification LSTM models are built on this dataset to identify if a given news headline text a clickbait headline or not.
- Model 1 calculates new embeddings during model developement.
- Model 2 uses Stanford's pre-trained glove embeddings
- This notebook covers the usual data cleaning steps for processing text data, and other functionalites in
tensorflow.keras.preprocessing.text
andtensorflow.keras.preprocessing.sequence
to transform and prepare text data so that it can used in an LSTM model.
- This notebook covers how to classify text data using an