This is the code repository for Deep learning for NLP using Python [Video], published by Packt. It contains all the supporting project files necessary to work through the video course from start to finish.
In this course, you’ll expand your NLP knowledge and skills while implementing deep learning tools to perform complex tasks. You’ll start by preparing your environment for NLP and then quickly learn about language structure and how we can break sentences down to extract information and uncover the underlying meaning. After reviewing the basics, we’ll move on to speech recognition and show how deep learning can be used to build speech recognition applications. In order to give you the best hands-on experience, the course includes a wide variety of practical real world examples. You’ll discover how a Naive Bayes algorithm can be used for Binary and Multiclass text classification. We’ll show you how a binary classifier can be used to determine if a product review would best be classified as positive or negative. You’ll also learn how document classifiers can be used to predict information about the author of a text like their age, gender, or where they’re from. Finally speech recognition systems will be introduced and you’ll learn how to apply deep learning techniques to build your own speech to text application. We’ll walk through two examples, step-by-step, showing how to build and train neural networks to understand spoken audio inputs. By the end of this tutorial, you’ll have a better understanding of NLP and will have worked on multiple examples that implement deep learning to solve real-world spoken language problems. In particular, you’ll be able to discover useful information and extract key insights from piles of natural language data.
- Learn how to build speech to text applications using deep learning.
- Implement deep learning with a convolution neural network, and a recurrent neural network using long-short term memory
- See how you can load, access, and use the built-in corpora of NLTK for linguistic research
- Create conditional frequency distributions for a given text dataset
- Utilize a lexical resource to organize text data and create relationships
- Process raw text with NLTK by implementing an NLP pipeline and implementing tokenization
- Use document classification algorithms to extract information about a text like the age and sentiment of the author
- Discover how the Naive-Bayes algorithm can be used for Binary and Multiclass text classification
- Understand the concepts of hierarchy of ideas, chunking, and chinking
- Use NLP to reduce long strings of information that can be difficult to analyze down into shorter, more manageable chunks of text data
To fully benefit from the coverage included in this course, you will need:
This video is for Python developers who have basic knowledge of NLP and want to make their NLP applications smarter by implementing deep learning.