دانلود کتاب پردازش زبان طبیعی در دنیای واقعی

In the modern day, data digitization has scaled and there are means to store every interaction happening across the world. Text data is heavily generated across the globe. Some common sources of text data include social media data, consumer inter- action, reviews, articles, documents, emails, and others. More and more businesses have started leveraging machine learning, and a large majority have some type of text data available to them. Over the last decade, several businesses have explored and been successful in getting intelligence out of text data generated by them or publicly available from the web. While many are on that path, many want to get on that path and exploit the potential of building data-driven offerings. Thus, knowing about NLP and how you can use it is prime in today’s time. Natural language processing (NLP) is a hot topic with a lot of applications and an increasing amount of research across the globe. NLP refers to a machine’s process to understand language. With the immense amount of text data generated today, there is an increase in the scope for leveraging NLP to build intelligent solutions. Google Trends suggests a 112% increase in searches on the topic of natural language processing in the past seven years. Many businesses today offer products and ser- vices powered by NLP. Common examples include Amazon Alexa, Gmail sentence auto-completion, and Google Translate for language translation. With the increasing demand for NLP-based products and services, there is a strong need for a workforce that is able to understand and implement NLP solutions. I started working in the industry as a Data Scientist after finishing grad school. At the time, I didn’t have any guidance in my field at the company I was working at. I was faced with tasks that seemed impossible to solve given my grad school back- ground. In an educational setting, you are working on defined problems. In the real world, you need to define these problems yourself given the knowledge of the business objective. In an educational setting, you have data available. You’re either working on publicly available datasets or one available at your educational institution. In the real world, you may not have labeled data, you may not have enough data, and you may not even have any data at all. Having faced these obstacles, I learned several lessons that over time helped me to excel at my work. I would often share my learnings and findings with the Python and Data Science community in the form of talks and presentations at conferences across the globe. After accumulating close to a decade of experience in working with language data and building NLP solutions in the real world, I wrote this book.