/Sentiment-Analysis-with-LSTM

Implementation of a Sentiment Analysis using Recurrent Neural Networks with LSTM cells

Primary LanguageJupyter Notebook

Sentiment Analysis with LSTMs

NOTE: This project is an optional excercise from Deep Learning Nanodegree by Udacity.

My solution: Jupyter notebook

Pytorch implementation of a Sentiment Analysis using Recurrent Neural Networks with LSTM cells. Using an RNN rather than a strictly feedforward network is more accurate since we can include information about the sequence of words.

Network Architecture

Related Work

I'm using an embedding layer as the first layer of the network. I did some works on implementing Skip-gram Word2Vec. This is a PyTorch implementation of Word2Vec algorithm using the Skip-gram architecture and Negative Sampling to improve both the quality of the vectors and the training speed. The main porpuse of this project is for me to learn about embedding words for use in Natural Language Processing.