Python natural language processing : explore NLP with machine learning and deep learning techniques / Jalaj Thanaki.

Format:

Book

Author/Creator:

Thanaki, Jalaj, author.

Language:

English

Subjects (All):

Python (Computer program language).

Natural language processing (Computer science).

Machine learning.

Physical Description:

1 online resource (476 pages) : illustrations

Edition:

1st ed.

Place of Publication:

Birmingham, England ; Mumbai, India : Packt Publishing, 2017.

Summary:

Leverage the power of machine learning and deep learning to extract information from text dataKey Features[*] Implement Machine Learning and Deep Learning techniques for efficient natural language processing[*] Get started with NLTK and implement NLP in your applications with ease[*] Understand and interpret human languages with the power of text analysis via PythonBook DescriptionThis book starts off by laying the foundation for Natural Language Processing and why Python is one of the best options to build an NLP-based expert system with advantages such as Community support, availability of frameworks and so on. Later it gives you a better understanding of available free forms of corpus and different types of dataset. After this, you will know how to choose a dataset for natural language processing applications and find the right NLP techniques to process sentences in datasets and understand their structure. You will also learn how to tokenize different parts of sentences and ways to analyze them. During the course of the book, you will explore the semantic as well as syntactic analysis of text. You will understand how to solve various ambiguities in processing human language and will come across various scenarios while performing text analysis. You will learn the very basics of getting the environment ready for natural language processing, move on to the initial setup, and then quickly understand sentences and language parts. You will learn the power of Machine Learning and Deep Learning to extract information from text data. By the end of the book, you will have a clear understanding of natural language processing and will have worked on multiple examples that implement NLP in the real world.What you will learn[*] Focus on Python programming paradigms, which are used to develop NLP applications[*] Understand corpus analysis and different types of data attribute.[*] Learn NLP using Python libraries such as NLTK, Polyglot, SpaCy, Standford CoreNLP and so on[*] Learn about Features Extraction and Feature selection as part of Features Engineering.[*] Explore the advantages of vectorization in Deep Learning.[*] Get a better understanding of the architecture of a rule-based system.[*] Optimize and fine-tune Supervised and Unsupervised Machine Learning algorithms for NLP problems.[*] Identify Deep Learning techniques for Natural Language Processing and Natural Language Generation problems.Who this book is forThis book is intended for Python developers who wish to start with natural language processing and want to make their applications smarter by implementing NLP in them.

Contents:

Cover

Copyright

Credits

Foreword

About the Author

Acknowledgement

About the Reviewers

www.PacktPub.com

Customer Feedback

Table of Contents

Preface

Chapter 1: Introduction

Understanding natural language processing

Understanding basic applications

Understanding advanced applications

Advantages of togetherness - NLP and Python

Environment setup for NLTK

Tips for readers

Summary

Chapter 2: Practical Understanding of a Corpus and Dataset

What is a corpus?

Why do we need a corpus?

Understanding corpus analysis

Exercise

Understanding types of data attributes

Categorical or qualitative data attributes

Numeric or quantitative data attributes

Exploring different file formats for corpora

Resources for accessing free corpora

Preparing a dataset for NLP applications

Selecting data

Preprocessing the dataset

Formatting

Cleaning

Sampling

Transforming data

Web scraping

Chapter 3: Understanding the Structure of a Sentences

Understanding components of NLP

Natural language understanding

Natural language generation

Differences between NLU and NLG

Branches of NLP

Defining context-free grammar

Morphological analysis

What is morphology?

What are morphemes?

What is a stem?

What is morphological analysis?

What is a word?

Classification of morphemes

Free morphemes

Bound morphemes

Derivational morphemes

Inflectional morphemes

What is the difference between a stem and a root?

Lexical analysis

What is a token?

What are part of speech tags?

Process of deriving tokens

Difference between stemming and lemmatization

Applications

Syntactic analysis

What is syntactic analysis?

Semantic analysis

What is semantic analysis?

Lexical semantics.

Hyponymy and hyponyms

Homonymy

Polysemy

What is the difference between polysemy and homonymy?

Application of semantic analysis

Handling ambiguity

Lexical ambiguity

Syntactic ambiguity

Approach to handle syntactic ambiguity

Semantic ambiguity

Pragmatic ambiguity

Discourse integration

Pragmatic analysis

Chapter 4: Preprocessing

Handling corpus-raw text

Getting raw text

Lowercase conversion

Sentence tokenization

Challenges of sentence tokenization

Stemming for raw text

Challenges of stemming for raw text

Lemmatization of raw text

Challenges of lemmatization of raw text

Stop word removal

Handling corpus-raw sentences

Word tokenization

Challenges for word tokenization

Word lemmatization

Challenges for word lemmatization

Basic preprocessing

Regular expressions

Basic level regular expression

Basic flags

Advanced level regular expression

Positive lookahead

Positive lookbehind

Negative lookahead

Negative lookbehind

Practical and customized preprocessing

Decide by yourself

Is preprocessing required?

What kind of preprocessing is required?

Understanding case studies of preprocessing

Grammar correction system

Sentiment analysis

Machine translation

Spelling correction

Approach

Chapter 5: Feature Engineering and NLP Algorithms

Understanding feature engineering

What is feature engineering?

What is the purpose of feature engineering?

Challenges

Basic feature of NLP

Parsers and parsing

Understanding the basics of parsers

Understanding the concept of parsing

Developing a parser from scratch

Types of grammar

Context-free grammar

Probabilistic context-free grammar

Calculating the probability of a tree.

Calculating the probability of a string

Grammar transformation

Developing a parser with the Cocke-Kasami-Younger Algorithm

Developing parsers step-by-step

Existing parser tools

The Stanford parser

The spaCy parser

Extracting and understanding the features

Customizing parser tools

POS tagging and POS taggers

Understanding the concept of POS tagging and POS taggers

Developing POS taggers step-by-step

Plug and play with existing POS taggers

A Stanford POS tagger example

Using polyglot to generate POS tagging

Using POS tags as features

Name entity recognition

Classes of NER

Plug and play with existing NER tools

A Stanford NER example

A Spacy NER example

n-grams

Understanding n-gram using a practice example

Application

Bag of words

Understanding BOW

Understanding BOW using a practical example

Comparing n-grams and BOW

Semantic tools and resources

Basic statistical features for NLP

Basic mathematics

Basic concepts of linear algebra for NLP

Basic concepts of the probabilistic theory for NLP

Probability

Independent event and dependent event

Conditional probability

TF-IDF

Understanding TF-IDF

Understanding TF-IDF with a practical example

Using textblob

Using scikit-learn

Vectorization

Encoders and decoders

One-hot encoding

Understanding a practical example for one-hot encoding

Normalization

The linguistics aspect of normalization

The statistical aspect of normalization

Probabilistic models

Understanding probabilistic language modeling

Application of LM

Indexing

Ranking

Advantages of features engineering

Challenges of features engineering.

Summary

Chapter 6: Advanced Feature Engineering and NLP Algorithms

Recall word embedding

Understanding the basics of word2vec

Distributional semantics

Defining word2vec

Necessity of unsupervised distribution semantic model - word2vec

Converting the word2vec model from black box to white box

Distributional similarity based representation

Understanding the components of the word2vec model

Input of the word2vec

Output of word2vec

Construction components of the word2vec model

Architectural component

Understanding the logic of the word2vec model

Vocabulary builder

Context builder

Neural network with two layers

Structural details of a word2vec neural network

Word2vec neural network layer's details

Softmax function

Main processing algorithms

Continuous bag of words

Skip-gram

Understanding algorithmic techniques and the mathematics behind the word2vec model

Understanding the basic mathematics for the word2vec algorithm

Techniques used at the vocabulary building stage

Lossy counting

Using it at the stage of vocabulary building

Techniques used at the context building stage

Dynamic window scaling

Understanding dynamic context window techniques

Subsampling

Pruning

Algorithms used by neural networks

Structure of the neurons

Basic neuron structure

Training a simple neuron

Define error function

Understanding gradient descent in word2vec

Single neuron application

Multi-layer neural networks

Backpropagation

Mathematics behind the word2vec model

Techniques used to generate final vectors and probability prediction stage

Hierarchical softmax

Negative sampling

Some of the facts related to word2vec

Applications of word2vec

Implementation of simple examples

Famous example (king - man + woman).

Advantages of word2vec

Challenges of word2vec

How is word2vec used in real-life applications?

When should you use word2vec?

Developing something interesting

Extension of the word2vec concept

Para2Vec

Doc2Vec

Applications of Doc2vec

GloVe

Importance of vectorization in deep learning

Chapter 7: Rule-Based System for NLP

Understanding of the rule-based system

What does the RB system mean?

Purpose of having the rule-based system

Why do we need the rule-based system?

Which kind of applications can use the RB approach over the other approaches?

What kind of resources do you need if you want to develop a rule-based system?

Architecture of the RB system

General architecture of the rule-based system as an expert system

Practical architecture of the rule-based system for NLP applications

Custom architecture - the RB system for NLP applications

Apache UIMA - the RB system for NLP applications

Understanding the RB system development life cycle

NLP applications using the rule-based system

Generalized AI applications using the rule-based system

Developing NLP applications using the RB system

Thinking process for making rules

Start with simple rules

Scraping the text data

Defining the rule for our goal

Coding our rule and generating a prototype and result

Python for pattern-matching rules for a proofreading application

Grammar correction

Template-based chatbot application

Flow of code

Advantages of template-based chatbot

Disadvantages of template-based chatbot

Comparing the rule-based approach with other approaches

Advantages of the rule-based system

Disadvantages of the rule-based system

Challenges for the rule-based system.

Understanding word-sense disambiguation basics.

Notes:

Includes index.

Description based on online resource; title from PDF title page (ebrary, viewed August 25, 2017).

OCLC:

999637356