Book Image

Natural Language Understanding with Python

By : Deborah A. Dahl
5 (1)
Book Image

Natural Language Understanding with Python

5 (1)
By: Deborah A. Dahl

Overview of this book

Natural Language Understanding facilitates the organization and structuring of language allowing computer systems to effectively process textual information for various practical applications. Natural Language Understanding with Python will help you explore practical techniques for harnessing NLU to create diverse applications. with step-by-step explanations of essential concepts and practical examples, you’ll begin by learning about NLU and its applications. You’ll then explore a wide range of current NLU techniques and their most appropriate use-case. In the process, you’ll be introduced to the most useful Python NLU libraries. Not only will you learn the basics of NLU, you’ll also discover practical issues such as acquiring data, evaluating systems, and deploying NLU applications along with their solutions. The book is a comprehensive guide that’ll help you explore techniques and resources that can be used for different applications in the future. By the end of this book, you’ll be well-versed with the concepts of natural language understanding, deep learning, and large language models (LLMs) for building various AI-based applications.
Table of Contents (21 chapters)
1
Part 1: Getting Started with Natural Language Understanding Technology
4
Part 2:Developing and Testing Natural Language Understanding Systems
16
Part 3: Systems in Action – Applying Natural Language Understanding at Scale

Choosing among preprocessing techniques

Table 5.2 is a summary of the preprocessing techniques described in this chapter, along with their advantages and disadvantages. It is important for every project to consider which techniques will lead to improved results:

Table 5.2 – Advantages and disadvantages of preprocessing techniques

Many techniques, such as spelling correction, have the potential to introduce errors because the technology is not perfect. This is particularly true for less well-studied languages, for which the relevant algorithms can be less mature than those of better-studied languages.

It is worth starting with an initial test with only the most necessary techniques (such as tokenization) and introducing additional techniques only if the results of the initial test are not good enough. Sometimes, the errors introduced by preprocessing can cause the overall results to get worse. It is important to keep evaluating results during...