Book Image

Cognitive Computing with IBM Watson

By : Rob High, Tanmay Bakshi
Book Image

Cognitive Computing with IBM Watson

By: Rob High, Tanmay Bakshi

Overview of this book

Cognitive computing is rapidly becoming a part of every aspect of our lives through data science, machine learning (ML), and artificial intelligence (AI). It allows computing systems to learn and keep on improving as the amount of data in the system increases. This book introduces you to a whole new paradigm of computing – a paradigm that is totally different from the conventional computing of the Information Age. You will learn the concepts of ML, deep learning (DL), neural networks, and AI with the help of IBM Watson APIs. This book will help you build your own applications to understand, and solve problems, and analyze them as per your needs. You will explore various domains of cognitive computing, such as NLP, voice processing, computer vision, emotion analytics, and conversational systems. Equipped with the knowledge of machine learning concepts, how computers do their magic, and the applications of these concepts, you’ll be able to research and apply cognitive computing in your projects.
Table of Contents (16 chapters)
Title Page
Copyright and Credits
About Packt
Contributors
Preface
Index

Training custom NMT models with Watson


As you've seen, neural machine translation through Watson is powerful. You're not limited to just word-based or phrase-based translation with Watson. Rather, it tries to understand the true meaning of the input; then, outputs the same intent in another language, even if it has different wording or sentence structuring.

However, natural language is a very broad domain; imagine trying to squeeze the entirety of human language —all of the expressions, vocabulary, domain-specific phrases, and more—into just one dataset and machine learning model. That's, unfortunately, not possible—there are just too many domains and fields, where specific lingo or jargon may be used.

That's why, with Watson, you're not just limited to the pre-trained models—you can train your own models, to tune the language in your own domain!

For example, as you can imagine, the word usage and sentence structure of United Nations speeches are different from the average email. Therefore...