English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 2h 24m | 457 MB
Use modern NLP tools & techniques with Deep Learning & PyTorch to build intelligent language applications
The 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.
A practical step by step approach for building intelligent language applications using NLP. You will first understand the intuition & logic behind each task then follow it with its implementation for an effective training of text & data processing with PyTorch.
What You Will Learn
- Processing insightful information from raw data using NLP techniques with PyTorch
- Working with PyTorch to take advantage of its maximum speed and flexibility
- Traditional and modern NLP methods & tools like NLTK, Spacy, Word2Vec & Gensim
- Implementing word embedding model and using it with the Gensim toolkit
- Sequence-to-sequence models (used in translation) that read one sequence & produces another
- Usage of LSTMs using PyTorch for Sentiment Analysis and how its different from RNNs
- Comparing and analysing results using Attention networks to improve your project’s performance
Table of Contents
Up and Running with PyTorch
1 The Course Overview
2 Using Deep Learning in Natural Language Processing
3 Functions and Features of PyTorch
4 Installing and Setting Up PyTorch
5 Understanding Sentiment Analysis and NMT
Data Cleaning and Preprocessing for Sentiment Analysis
6 NLTK and spaCy Installations
7 Tokenization with NLTK
8 Stop Words
9 Lemmatization
10 Pipelines
Implement Word Embeddings with gensim
11 Working with Word Embeddings
12 Setting Up and Installing gensim
13 Exploring Word Embeddings with gensim
14 Understanding the Embeddings Created
15 Pretrained Embeddings Using Word2vec
Train RNNs and LSTMs Units for Sentiment Analysis
16 Working with Recurrent Neural Network
17 Implementing RNN
18 Results with RNN
19 Working with LSTM
20 Implementing LSTM
21 Results with LSTM
Build a Neural Machine Translator
22 Intro to seq2seq
23 Installations
24 Implementing seq2seq – Encoder
25 Implementing seq2seq – Decoder
26 Results with seq2seq
Improve the Neural Machine Translation with Attention Networks
27 Introduction to Attention Networks
28 Implementing seq2seq – Encoder
29 Results with Attention Network
30 The Way Forward
Resolve the captcha to access the links!