In the digital information age that we live in, the amount of data has grown exponentially, and it is growing at an unprecedented rate as we read this. Most of this data is language-related data (textual or verbal), such as emails, social media posts, phone calls, and web articles. Natural Language Processing (NLP) leverages this data efficiently to help humans in their businesses or day-to-day tasks. NLP has already revolutionized the way we use data to improve both businesses and our lives, and will continue to do so in the future.

One of the most ubiquitous use cases of NLP is Virtual Assistants (VAs), such as Apple's Siri, Google Assistant, and Amazon Alexa. Whenever you ask your VA for "the cheapest rates for hotels in Switzerland," a complex series of NLP tasks are triggered. First, your VA needs to understand (parse) your request (for example, learn that it needs to retrieve hotel rates, not the dog parks). Another decision the VA needs to make is "what is cheap?". Next, the VA needs to rank the cities in Switzerland (perhaps based on your past traveling history). Then, the VA might crawl websites such as Booking.com and Agoda.com to fetch the hotel rates in Switzerland and rank them by analyzing both the rates and reviews for each hotel. As you can see, the results you see in a few seconds are a result of a very intricate series of complex NLP tasks.

So, what makes such NLP tasks so versatile and accurate for our everyday tasks? The underpinning elements are "deep learning" algorithms. Deep learning algorithms are essentially complex neural networks that can map raw data to a desired output without requiring any sort of task-specific feature engineering. This means that you can provide a hotel review of a customer and the algorithm can answer the question "How positive is the customer about this hotel?", directly. Also, deep learning has already reached, and even exceeded, human-level performance in a variety of NLP tasks (for example, speech recognition and machine translation).

By reading this book, you will learn how to solve many interesting NLP problems using deep learning. So, if you want to be an influencer who changes the world, studying NLP is critical. These tasks range from learning the semantics of words, to generating fresh new stories, to performing language translation just by looking at bilingual sentence pairs. All of the technical chapters are accompanied by exercises, including step-by-step guidance for readers to implement these systems. For all of the exercises in the book, we will be using Python with TensorFlow—a popular distributed computation library that makes implementing deep neural networks very convenient.