Book Image

Advanced Natural Language Processing with TensorFlow 2

By : Ashish Bansal, Tony Mullen
Book Image

Advanced Natural Language Processing with TensorFlow 2

By: Ashish Bansal, Tony Mullen

Overview of this book

Recently, there have been tremendous advances in NLP, and we are now moving from research labs into practical applications. This book comes with a perfect blend of both the theoretical and practical aspects of trending and complex NLP techniques. The book is focused on innovative applications in the field of NLP, language generation, and dialogue systems. It helps you apply the concepts of pre-processing text using techniques such as tokenization, parts of speech tagging, and lemmatization using popular libraries such as Stanford NLP and SpaCy. You will build Named Entity Recognition (NER) from scratch using Conditional Random Fields and Viterbi Decoding on top of RNNs. The book covers key emerging areas such as generating text for use in sentence completion and text summarization, bridging images and text by generating captions for images, and managing dialogue aspects of chatbots. You will learn how to apply transfer learning and fine-tuning using TensorFlow 2. Further, it covers practical techniques that can simplify the labelling of textual data. The book also has a working code that is adaptable to your use cases for each tech piece. By the end of the book, you will have an advanced knowledge of the tools, techniques and deep learning architecture used to solve complex NLP problems.
Table of Contents (13 chapters)
Other Books You May Enjoy

Essentials of NLP

Language has been a part of human evolution. The development of language allowed better communication between people and tribes. The evolution of written language, initially as cave paintings and later as characters, allowed information to be distilled, stored, and passed on from generation to generation. Some would even say that the hockey stick curve of advancement is because of the ever-accumulating cache of stored information. As this stored information trove becomes larger and larger, the need for computational methods to process and distill the data becomes more acute. In the past decade, a lot of advances were made in the areas of image and speech recognition. Advances in Natural Language Processing (NLP) are more recent, though computational methods for NLP have been an area of research for decades. Processing textual data requires many different building blocks upon which advanced models can be built. Some of these building blocks themselves can be quite challenging and advanced. This chapter and the next focus on these building blocks and the problems that can be solved with them through simple models.

In this chapter, we will focus on the basics of pre-processing text and build a simple spam detector. Specifically, we will learn about the following:

  • The typical text processing workflow
  • Data collection and labeling
  • Text normalization, including case normalization, text tokenization, stemming, and lemmatization
    • Modeling datasets that have been text normalized
    • Vectorizing text
    • Modeling datasets with vectorized text

Let's start by getting to grips with the text processing workflow most NLP models use.