Skip to content

Collection of Notebooks for Natural Language Processing with PyTorch

Notifications You must be signed in to change notification settings

jibinmathew69/Hands-on-NLP-with-PyTorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Hands-on-NLP-with-PyTorch

Collection of Notebooks for Natural Language Processing with PyTorch

This notebook contains all the code for the course that I did for PacktPub.

The sections are divided by folders.

The topics that are covered are:

1.UP AND RUNNING WITH PYTORCH
In this section, you setup our environment for PyTorch and learn to perform some basic operations with PyTorch and build quick Neural network with PyTorch and also understand why Deep Learning is a useful technique for NLP.

2.DATA CLEANING AND PREPROCESSING FOR SENTIMENT ANALYSIS
In this section, you will learn the use of tools like NLTK and Spacy as NLP libraries and how they help in data preprocessing. You will clean your data with NLTK then parse and lemmatize the data with Spacy and understand pipelines.

3.IMPLEMENT WORD EMBEDDINGS WITH GENSIM
In this section, you will discover the conceptual relationship in a text and how they help in overall understanding Text. You will perform hands on operations with Gensim library.

4.TRAIN RNNS AND LSTMS UNITS FOR SENTIMENT ANALYSIS
In this section, you will deep dive into Deep Learning and implement RNNs for our Sentiment Analysis, and further improve the performance with advanced architectures and LSTM.

5.BUILD A NEURAL MACHINE TRANSLATOR
In this section, you will learn an important Deep Learning architecture within NLP called Sequence-to-sequence and learn to appreciate its applications and complete our project to build a Neural Translation Machine.

6.IMPROVE THE NEURAL MACHINE TRANSLATION WITH ATTENTION NETWORKS
In this section, you will deep dive into Deep Learning and implement RNNs for our Sentiment Analysis, and further improve the performance with advanced architectures and LSTM.