Advertisement

Neural Representations of Natural Language

  • Lyndon White
  • Roberto Togneri
  • Wei Liu
  • Mohammed Bennamoun

Part of the Studies in Computational Intelligence book series (SCI, volume 783)

Table of contents

  1. Front Matter
    Pages i-xiv
  2. Lyndon White, Roberto Togneri, Wei Liu, Mohammed Bennamoun
    Pages 1-21
  3. Lyndon White, Roberto Togneri, Wei Liu, Mohammed Bennamoun
    Pages 23-36
  4. Lyndon White, Roberto Togneri, Wei Liu, Mohammed Bennamoun
    Pages 37-71
  5. Lyndon White, Roberto Togneri, Wei Liu, Mohammed Bennamoun
    Pages 73-92
  6. Lyndon White, Roberto Togneri, Wei Liu, Mohammed Bennamoun
    Pages 93-114
  7. Lyndon White, Roberto Togneri, Wei Liu, Mohammed Bennamoun
    Pages 115-119
  8. Back Matter
    Pages 121-122

About this book

Introduction

This book offers an introduction to modern natural language processing using machine learning, focusing on how neural networks create a machine interpretable representation of the meaning of natural language. Language is crucially linked to ideas – as Webster’s 1923 “English Composition and Literature” puts it: “A sentence is a group of words expressing a complete thought”. Thus the representation of sentences and the words that make them up is vital in advancing artificial intelligence and other “smart” systems currently being developed. Providing an overview of the research in the area, from Bengio et al.’s seminal work on a “Neural Probabilistic Language Model” in 2003, to the latest techniques, this book enables readers to gain an understanding of how the techniques are related and what is best for their purposes. As well as a introduction to neural networks in general and recurrent neural networks in particular, this book details the methods used for representing words, senses of words, and larger structures such as sentences or documents. The book highlights practical implementations and discusses many aspects that are often overlooked or misunderstood. The book includes thorough instruction on challenging areas such as hierarchical softmax and negative sampling, to ensure the reader fully and easily understands the details of how the algorithms function. Combining practical aspects with a more traditional review of the literature, it is directly applicable to a broad readership. It is an invaluable introduction for early graduate students working in natural language processing; a trustworthy guide for industry developers wishing to make use of recent innovations; and a sturdy bridge for researchers already familiar with linguistics or machine learning wishing to understand the other.

Keywords

Natural Language Processing Machine Learning Vector Representations Word Embeddings Learned Representations Word Sense Representations Phrase Representations Sentence Representations Character-Based Representations Language Modeling

Authors and affiliations

  • Lyndon White
    • 1
  • Roberto Togneri
    • 2
  • Wei Liu
    • 3
  • Mohammed Bennamoun
    • 4
  1. 1.Department of Electrical, Electronic and Computer Engineering, School of Engineering, Faculty of Engineering and Mathematical SciencesThe University of Western AustraliaPerthAustralia
  2. 2.Department of Electrical, Electronic and Computer Engineering, School of Engineering, Faculty of Engineering and Mathematical SciencesThe University of Western AustraliaPerthAustralia
  3. 3.Department of Computer Science and Software Engineering, School of Physics, Mathematics and Computing, Faculty of Engineering and Mathematical SciencesThe University of Western AustraliaPerthAustralia
  4. 4.Department of Computer Science and Software Engineering, School of Physics, Mathematics and Computing, Faculty of Engineering and Mathematical SciencesThe University of Western AustraliaPerthAustralia

Bibliographic information