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

Natural language translation – the past 


Traditionally, Language Translation (LT) has been a very involved  process—people have thought that only humans can really logically translate from one language to another. It requires a uniquely human representation and understanding of the contents of a sentence, paragraph, or document. LT is more than just understanding sentiment—it's about recreating the input data in a different style. It's complex due to the various words, word types, and sentence structures of different languages, and for the following reasons:

  • Some words don't have gender attributes
  • Some have gender attributes for everything—a chair can be masculine or feminine in German
  • Most don't have the word you
  • Most languages, such as French, don't have a literal translation of the English word for fun

Therefore, for the past few decades, the majority of research on LT techniques were best effort—they'd do word-to-word or phrase-to-phrase translations, but they wouldn't create natural-sounding...