Natural Language Processing and Computational Linguistics

By : Bhargav Srinivasa-Desikan

3.6 (7)

Buy this Book

Natural Language Processing and Computational Linguistics

3.6 (7)

By: Bhargav Srinivasa-Desikan

Buy this Book

Overview of this book

Modern text analysis is now very accessible using Python and open source tools, so discover how you can now perform modern text analysis in this era of textual data. This book shows you how to use natural language processing, and computational linguistics algorithms, to make inferences and gain insights about data you have. These algorithms are based on statistical machine learning and artificial intelligence techniques. The tools to work with these algorithms are available to you right now - with Python, and tools like Gensim and spaCy. You'll start by learning about data cleaning, and then how to perform computational linguistics from first concepts. You're then ready to explore the more sophisticated areas of statistical NLP and deep learning using Python, with realistic language and text samples. You'll learn to tag, parse, and model text using the best tools. You'll gain hands-on knowledge of the best frameworks to use, and you'll know when to choose a tool like Gensim for topic models, and when to work with Keras for deep learning. This book balances theory and practical hands-on examples, so you can learn about and conduct your own natural language processing projects and computational linguistics. You'll discover the rich ecosystem of Python tools you have available to conduct NLP - and enter the interesting world of modern text analysis.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

What is Text Analysis?

What is text analysis?

Where's the data at?

Garbage in, garbage out

Why should you do text analysis?

Summary

References

Python Tips for Text Analysis

Why Python?

Text manipulation in Python

Summary

References

spaCy's Language Models

spaCy

Installation

Tokenizing text

Summary

References

Gensim – Vectorizing Text and Transformations and n-grams

Introducing Gensim

Vectors and why we need them

Vector transformations in Gensim

n-grams and some more preprocessing

Summary

References

POS-Tagging and Its Applications

What is POS-tagging?

POS-tagging in Python

Training our own POS-taggers

POS-tagging code examples

Summary

References

NER-Tagging and Its Applications

What is NER-tagging?

NER-tagging in Python

Training our own NER-taggers

NER-tagging examples and visualization

Summary

References

Dependency Parsing

Dependency parsing

Dependency parsing in Python

Dependency parsing with spaCy

Training our dependency parsers

Summary

References

Topic Models

What are topic models?

Topic models in Gensim

Topic models in scikit-learn

Summary

References

Advanced Topic Modeling

Advanced training tips

Exploring documents

Topic coherence and evaluating topic models

Visualizing topic models

Summary

References

Clustering and Classifying Text

Clustering text

Starting clustering

K-means

Hierarchical clustering

Classifying text

Summary

References

Similarity Queries and Summarization

Similarity metrics

Similarity queries

Summarizing text

Summary

References

Word2Vec, Doc2Vec, and Gensim

Word2Vec

Doc2Vec

Other word embeddings

Summary

References

Deep Learning for Text

Deep learning

Deep learning for text (and more)

Generating text

Summary

References

Keras and spaCy for Deep Learning

Keras and spaCy

Classification with Keras

Classification with spaCy

Summary

References

Sentiment Analysis and ChatBots

Sentiment analysis

ChatBots

Summary

References

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

3.6 (7)

5 star

42.9%

4 star

14.3%

3 star

14.3%

2 star

14.3%

1 star

14.3%

Introducing Gensim

So far, we haven't spoken much about finding hidden information - more about how to get our textual data in shape. We will be taking a brief departure from spaCy to discuss vector spaces and the open source Python package Gensim - this is because some of these concepts will be useful in the upcoming chapters and we would like to lay the foundation before moving on. However, we'll only be touching the surface of Gensim's capabilities. This chapter will introduce you to the data structures largely used in text analysis involving machine learning techniques - vectors [1].

This means that we are still in the domain of preprocessing and getting our data ready for further machine learning analysis. It may seem like overkill, focusing so much on just setting up our text/data, but like we've said before - garbage in, garbage out. While the previous...