Last updated 1/2018MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHzLanguage: English | Size: 592.19 MB | Duration: 5h 53m

What you'll learn

Understand how NLP can be used

Explain basic, commonly used NLP tasks

Understand how NLP models are created and used

Use various techniques to acquire and clean data

Split text into individual sentences

Identify names, dates, and locations

Identify the grammatical parts of a sentence

Classify documents by type

Detee the sennt of text

Requirements

Basic working knowledge of Java is needed

Description

Natural Language Processing is used in many applications to provide capabilities that were previously not possible. It involves analyzing text to obtain the intent and meaning, which can then be used to support an application. Using NLP within an application requires a combination of standard Java techniques and often specialized libraries frequently based on models that have been trained. If you're interested to learn the powerful Natural Language Processing techniques with Java, then go for this Learning Path.

Packt’s Video Learning Paths are a series of individual video products put together in a logical and stepwise manner such that each video builds on the skills learned in the video before it.

The highlights of this Learning Path are:

Perform tokenization based on specific text processing needs

Extract the relationship between elements of text

This Learning Path covers the essence of NLP using Java. This Learning Path will commence by walking you through basic NLP tasks including data acquisition, data cleaning, finding parts of text, and deteing the end of sentences. These serve as the basis for other NLP tasks such as classifying text and deteing the relationship between text elements. This will be followed by the use of tokenization techniques. Tokenization is used for almost all NLP tasks. You’ll learn how text can be split to reveal information such as names, dates, and even the grammatical structure of a sentence. These types of activity can lead to insights into the relationships between text elements and embedded meaning in a document.

You'll then start by building on the basic NLP tasks of data normalization, tokenization, and SBD to perform more specialized NLP tasks. You’ll be able to do more than simply find a word in the text. You'll also identify specific elements such as a person’s name or a location from the text. Finally, you'll learn to split a sentence into basic grammatical units is another task that enables you to extract meaning and relationships from text.

Towards the end of this Learning Path, you will be ready to take on more advanced NLP tasks with Natural Language Processing techniques using Java.

Meet Your Experts

We have combined the best works of the following esteemed authors to ensure that your learning journey is smooth

Kamesh Balasubramanian is the founder and CEO of Wirecog, LLC. He is the inventor of Wireframe Cognition (Wirecog), an award-winning, patented technology that allows machines to understand wireframe designs and produce source code from them. Kamesh has over 20 years' software development experience and has implemented numerous solutions in the advertising, entertainment, media, publishing, hospitality, videogame, legal, and government sectors. He is an award-winning, professional member of the Association for Computing Machinery and an InfyMaker Award winner. He was recognized as a Maker of Change at the 2016 World Maker Faire in New York and, upon request, has demonstrated Wirecog at MIT.

Ben Tranter is a developer with nearly six years’ experience. He has worked with a variety of companies to build applications in Go, in the areas of data mining, web back ends, user authentication services, and developer tools, and is a contributor to a variety of open source Go projects.

Rostislav Dzinko is a software architect who has been working in the software development industry for more than six years. He was one of the first developers who started working with the Go language far earlier than the first official public release of Go 1.0 took place. Rostislav uses the Go language daily and has successfully used it in production for more than two years, building a broad range of software from high-load web applications to command-line utilities. He has a Master’s degree in Systems Eeering and has completed a PhD thesis.

Overview

Section 1: Getting Started with Natural Language Processing in Java

Lecture 1 The Course Overview

Lecture 2 Installation and Setup

Lecture 3 How NLP is Used

Lecture 4 Text Processing Tasks

Lecture 5 Understanding NLP Models

Lecture 6 Java Support for NLP

Lecture 7 Extracting Text from a Web Page

Lecture 8 Using Bliki to Access

Lecture 9 Accessing Data from Common File Formats

Lecture 10 Accessing Text from a PDF File

Lecture 11 Perfog Basic Cleaning Operations

Lecture 12 Removing Stop Words

Lecture 13 Validating Data

Lecture 14 Simple Java Tokenizers

Lecture 15 Specialized Java Tokenizers

Lecture 16 Applying Stemming and Lemmatization to Text

Lecture 17 What Makes SBD Difficult

Lecture 18 Simple Java SBDs

Lecture 19 Using Specialized SBD APIs

Lecture 20 Training a SBD Model

Section 2: Finding Elements of Text with NLP in Java

Lecture 21 The Course Overview

Lecture 22 The Nature and Problems Associated with NER

Lecture 23 Using Regular Expression for NER

Lecture 24 Using NLP API's for NER

Lecture 25 Training a Model for NER

Lecture 26 Understanding POS

Lecture 27 Using NLP API’s for POS Processing

Lecture 28 Training a POS Model

Lecture 29 Text Classification and Sennt Analysis

Lecture 30 Classifying Text Using NLP Models

Lecture 31 Perfog Sennt Analysis

Lecture 32 Understanding Relationship Types and Parse Trees

Lecture 33 Extracting Relationships Using NLP API’s

Lecture 34 Finding Word Dependencies and Coreference Resolution Entities

This Learning Path is aimed at Java developers who wish to learn the basics of NLP. Such developers will be working on applications that can benefit from text analysis, whether from providing more sophisticated processing of user input, or adding analytical capabilities to enhance the user's understanding of an application's data sets.

HomePage: