by Jibin Mathew | Released January 2019 | ISBN: 9781789133974

Build smart language applications using Deep LearningAbout This VideoExtensive practical training to understand the combined working of NLP, deep learning, and PyTorchWork with both traditional & modern NLP tools like NLTK, SpaCy & Word2Vec for creating real world NLP models.Each chapter includes several code examples and illustrations for an in-depth understanding of performing complex NLP tasksIn DetailThe main goal of this course is to train you to perform complex NLP tasks (and build intelligent language applications) using Deep Learning with PyTorch.You will build two complete real-world NLP applications throughout the course. The first application is a Sentiment Analyzer that analyzes data to determine whether a review is positive or negative towards a particular movie. You will then create an advanced Neural Translation Machine that is a speech translation engine, using Sequence to Sequence models with the speed and flexibility of PyTorch to translate given text into different languages.By the end of the course, you will have the skills to build your own real-world NLP models using PyTorch's Deep Learning capabilities.The code bundle for this video course is available at - https://github.com/PacktPublishing/Hands-On-Natural-Language-Processing-with-PytorchDownloading the example code for this course: You can download the example code files for all Packt video courses you have purchased from your account at http://www.PacktPub.com. If you purchased this course elsewhere, you can visit http://www.PacktPub.com/support and register to have the files e-mailed directly to you. Show and hide more

1. Chapter 1 : Up and Running with PyTorch
   • The Course Overview 00:02:48
   • Using Deep Learning in Natural Language Processing 00:02:17
   • Functions and Features of PyTorch 00:03:46
   • Installing and Setting Up PyTorch 00:02:11
   • Understanding Sentiment Analysis and NMT 00:04:41
2. Chapter 2 : Data Cleaning and Preprocessing for Sentiment Analysis
   • NLTK and spaCy Installations 00:02:28
   • Tokenization with NLTK 00:06:11
   • Stop Words 00:05:23
   • Lemmatization 00:04:18
   • Pipelines 00:04:05
3. Chapter 3 : Implement Word Embeddings with gensim
   • Working with Word Embeddings 00:04:17
   • Setting Up and Installing gensim 00:00:49
   • Exploring Word Embeddings with gensim 00:03:07
   • Understanding the Embeddings Created 00:03:41
   • Pretrained Embeddings Using Word2vec 00:03:09
4. Chapter 4 : Train RNNs and LSTMs Units for Sentiment Analysis
   • Working with Recurrent Neural Network 00:05:09
   • Implementing RNN 00:14:34
   • Results with RNN 00:09:35
   • Working with LSTM 00:05:33
   • Implementing LSTM 00:06:08
   • Results with LSTM 00:04:53
5. Chapter 5 : Build a Neural Machine Translator
   • Intro to seq2seq 00:02:25
   • Installations 00:01:07
   • Implementing seq2seq – Encoder 00:08:21
   • Implementing seq2seq – Decoder 00:05:30
   • Results with seq2seq 00:07:30
6. Chapter 6 : Improve the Neural Machine Translation with Attention Networks
   • Introduction to Attention Networks 00:03:28
   • Implementing seq2seq – Encoder 00:07:32
   • Results with Attention Network 00:06:25
   • The Way Forward 00:03:19
Show and hide more