Book Image

Hands-On Python Natural Language Processing

By : Aman Kedia, Mayank Rasu
Book Image

Hands-On Python Natural Language Processing

By: Aman Kedia, Mayank Rasu

Overview of this book

Natural Language Processing (NLP) is the subfield in computational linguistics that enables computers to understand, process, and analyze text. This book caters to the unmet demand for hands-on training of NLP concepts and provides exposure to real-world applications along with a solid theoretical grounding. This book starts by introducing you to the field of NLP and its applications, along with the modern Python libraries that you'll use to build your NLP-powered apps. With the help of practical examples, you’ll learn how to build reasonably sophisticated NLP applications, and cover various methodologies and challenges in deploying NLP applications in the real world. You'll cover key NLP tasks such as text classification, semantic embedding, sentiment analysis, machine translation, and developing a chatbot using machine learning and deep learning techniques. The book will also help you discover how machine learning techniques play a vital role in making your linguistic apps smart. Every chapter is accompanied by examples of real-world applications to help you build impressive NLP applications of your own. By the end of this NLP book, you’ll be able to work with language data, use machine learning to identify patterns in text, and get acquainted with the advancements in NLP.
Table of Contents (16 chapters)
1
Section 1: Introduction
4
Section 2: Natural Language Representation and Mathematics
9
Section 3: NLP and Learning

BERT

The embeddings that we created when discussing Word2vec and fastText were static in the sense that no matter what context a word was being used in, its embedding would be the same.

Let's consider an example to understand this:

Apple is a fruit

Apple is a company

In both these sentences, no matter what context Apple is being used in, the embeddings for the word would be the same. Instead, we should work on building techniques that can provide representations of a word based on the current context it is being used in.

Moreover, we need to build semi-supervised models that could be pre-trained on a broader task and later be fine-tuned to a specific task. The knowledge built while solving the broader task could be applied to solve a different but related task. This is referred to as transfer learning.

BERT catered to both our aforementioned problems in its own unique way. Researchers at Google developed BERT and made the methodology that they used to build BERT open source, along...