Machine Reading Comprehension

Book description

Machine reading comprehension (MRC) is a cutting-edge technology in natural language processing (NLP). MRC has recently advanced significantly, surpassing human parity in several public datasets. It has also been widely deployed by industry in search engine and quality assurance systems. Machine Reading Comprehension: Algorithms and Practice performs a deep-dive into MRC, offering a resource on the complex tasks this technology involves. The title presents the fundamentals of NLP and deep learning, before introducing the task, models, and applications of MRC. This volume gives theoretical treatment to solutions and gives detailed analysis of code, and considers applications in real-world industry. The book includes basic concepts, tasks, datasets, NLP tools, deep learning models and architecture, and insight from hands-on experience. In addition, the title presents the latest advances from the past two years of research. Structured into three sections and eight chapters, this book presents the basis of MRC; MRC models; and hands-on issues in application. This book offers a comprehensive solution for researchers in industry and academia who are looking to understand and deploy machine reading comprehension within natural language processing.

  • Presents the first comprehensive resource on machine reading comprehension (MRC)
  • Performs a deep-dive into MRC, from fundamentals to latest developments
  • Offers the latest thinking and research in the field of MRC, including the BERT model
  • Provides theoretical discussion, code analysis, and real-world applications of MRC
  • Gives insight from research which has led to surpassing human parity in MRC

Table of contents

  1. Cover image
  2. Title page
  3. Table of Contents
  4. Copyright
  5. About the author
  6. Foreword by Xuedong Huang
  7. Foreword by Zide Du
  8. Preface
    1. Acknowledgment
  9. Recommendation
  10. Part I: Foundation
    1. Chapter 1. Introduction to machine reading comprehension
      1. Abstract
      2. 1.1 The machine reading comprehension task
      3. 1.2 Natural language processing
      4. 1.3 Deep learning
      5. 1.4 Evaluation of machine reading comprehension
      6. 1.5 Machine reading comprehension datasets
      7. 1.6 How to make an machine reading comprehension dataset
      8. 1.7 Summary
      9. References
    2. Chapter 2. The basics of natural language processing
      1. Abstract
      2. 2.1 Tokenization
      3. 2.2 The cornerstone of natural language processing: word vectors
      4. 2.3 Linguistic tagging
      5. 2.4 Language model
      6. 2.5 Summary
      7. Reference
    3. Chapter 3. Deep learning in natural language processing
      1. Abstract
      2. 3.1 From word vector to text vector
      3. 3.2 Answer multiple-choice questions: natural language understanding
      4. 3.3 Write an article: natural language generation
      5. 3.4 Keep focused: attention mechanism
      6. 3.5 Summary
  11. Part II: Architecture
    1. Chapter 4. Architecture of machine reading comprehension models
      1. Abstract
      2. 4.1 General architecture of machine reading comprehension models
      3. 4.2 Encoding layer
      4. 4.3 Interaction layer
      5. 4.4 Output layer
      6. 4.5 Summary
      7. References
    2. Chapter 5. Common machine reading comprehension models
      1. Abstract
      2. 5.1 Bidirectional attention flow model
      3. 5.2 R-NET
      4. 5.3 FusionNet
      5. 5.4 Essential-term-aware retriever–reader
      6. 5.5 Summary
      7. References
    3. Chapter 6. Pretrained language models
      1. Abstract
      2. 6.1 Pretrained models and transfer learning
      3. 6.2 Translation-based pretrained language model: CoVe
      4. 6.3 Pretrained language model ELMo
      5. 6.4 The generative pretraining language model: generative pre-training (GPT)
      6. 6.5 The phenomenal pretrained language model: BERT
      7. 6.6 Summary
      8. References
  12. Part III: Application
    1. Chapter 7. Code analysis of the SDNet model
      1. Abstract
      2. 7.1 Multiturn conversational machine reading comprehension model: SDNet
      3. 7.2 Introduction to code
      4. 7.3 Preprocessing
      5. 7.4 Training
      6. 7.5 Batch generator
      7. 7.6 SDNet model
      8. 7.7 Summary
      9. Reference
    2. Chapter 8. Applications and future of machine reading comprehension
      1. Abstract
      2. 8.1 Intelligent customer service
      3. 8.2 Search engine
      4. 8.3 Health care
      5. 8.4 Laws
      6. 8.5 Finance
      7. 8.6 Education
      8. 8.7 The future of machine reading comprehension
      9. 8.8 Summary
      10. References
  13. Appendix A. Machine learning basics
    1. A.1 Types of machine learning
    2. A.2 Model and parameters
    3. A.3 Generalization and overfitting
  14. Appendix B. Deep learning basics
    1. B.1 Neural network
    2. B.2 Common types of neural network in deep learning
    3. B.3 The deep learning framework PyTorch
  15. Index

Product information

  • Title: Machine Reading Comprehension
  • Author(s): Chenguang Zhu
  • Release date: March 2021
  • Publisher(s): Elsevier
  • ISBN: 9780323901192