Natural-Language-Processing---Sequence-Data-world

This repo is purely inspired from Andrew Ng's Coursera course called Deep learning specialization

Natural Language Processing

In this data world, sequence data is one of the challenging thing to get processed. But fortunately Deep neural networks helps us to process this data and ease the way to get valuable results.

Repository Author Info - G DHAMODHARAN, MSc Computer Science, Anna University.

NLP has a wide range of applications like,

                                     * Speech Recognition
                                     * Dialog Systems
                                     * Sentiment Analysis
                                     * Machine Translation
                                     * Video Activity Recognition
                                     * Name Entity Recognition
                                     * Creation of Question and Answers with Distraction for MCQ based tests
                                     * and Many more...

To learn NLP, We must master RNN - Recurrent Neural Networks. I designed this repo something like this( Thanks to Standford CheatSheet )

Basics

                                  * Architecture structure
                                  * Applications of RNNs
                                  * Loss function
                                  * Backpropagation

Handling long term dependencies

                                  * Common activation functions 
                                  * Vanishing/exploding gradient
                                  * Gradient clipping
                                  * GRU/LSTM
                                  * Types of gates
                                  * Bidirectional RNN
                                  * Deep RNN

Learning word representation

                                  * Notations
                                  * Embedding matrix
                                  * Word2vec
                                  * Skip-gram
                                  * Negative sampling
                                  * GloVe

Comparing words

                                  * Cosine similarity
                                  * t-SNE
                                  * Language model
                                  * n-gram
                                  * Perplexity

Machine translation

                                  * Beam search
                                  * Length normalization
                                  * Error analysis
                                  * Bleu score

Attention

                                  * Attention model
                                  * Attention weights