Deep Learning for Search

Deep Learning for Search

by Tommaso Teofili
Released June 2019
Publisher(s): Manning Publications
ISBN: 9781617294792

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Deep Learning for Search teaches you how to improve the effectiveness of your search by implementing neural network-based techniques. By the time you're finished with the book, you'll be ready to build amazing search engines that deliver the results your users need and that get better as time goes on!



About the Technology

Deep learning handles the toughest search challenges, including imprecise search terms, badly indexed data, and retrieving images with minimal metadata. And with modern tools like DL4J and TensorFlow, you can apply powerful DL techniques without a deep background in data science or natural language processing (NLP). This book will show you how.



About the Book

Deep Learning for Search teaches you to improve your search results with neural networks. You’ll review how DL relates to search basics like indexing and ranking. Then, you’ll walk through in-depth examples to upgrade your search with DL techniques using Apache Lucene and Deeplearning4j. As the book progresses, you’ll explore advanced topics like searching through images, translating user queries, and designing search engines that improve as they learn!



What's Inside

  • Accurate and relevant rankings
  • Searching across languages
  • Content-based image search
  • Search with recommendations


About the Reader

For developers comfortable with Java or a similar language and search basics. No experience with deep learning or NLP needed.



About the Author

Tommaso Teofili is a software engineer with a passion for open source and machine learning. As a member of the Apache Software Foundation, he contributes to a number of open source projects, ranging from topics like information retrieval (such as Lucene and Solr) to natural language processing and machine translation (including OpenNLP, Joshua, and UIMA).

He currently works at Adobe, developing search and indexing infrastructure components, and researching the areas of natural language processing, information retrieval, and deep learning. He has presented search and machine learning talks at conferences including BerlinBuzzwords, International Conference on Computational Science, ApacheCon, EclipseCon, and others. You can find him on Twitter at @tteofili.



Quotes
A practical approach that shows you the state of the art in using neural networks, AI, and deep learning in the development of search engines.
- From the Foreword by Chris Mattmann, NASA JPL

A thorough and thoughtful synthesis of traditional search and the latest advancements in deep learning.
- Greg Zanotti, Marquette Partners

A well-laid-out deep dive into the latest technologies that will take your search engine to the next level.
- Andrew Wyllie, Thynk Health

Hands-on exercises teach you how to master deep learning for search-based products.
- Antonio Magnaghi, System1

Table of contents

  1. Copyright
  2. Brief Table of Contents
  3. Table of Contents
  4. Foreword
  5. Preface
  6. Acknowledgments
  7. About this book
  8. About the author
  9. About the cover illustration
  10. Part 1. Search meets deep learning
    1. Chapter 1. Neural search
      1. 1.1. Neural networks and deep learning
      2. 1.2. What is machine learning?
      3. 1.3. What deep learning can do for search
      4. 1.4. A roadmap for learning deep learning
      5. 1.5. Retrieving useful information
      6. 1.6. Unsolved problems
      7. 1.7. Opening the search engine black box
      8. 1.8. Deep learning to the rescue
      9. 1.9. Index, please meet neuron
      10. 1.10. Neural network training
      11. 1.11. The promises of neural search
      12. Summary
    2. Chapter 2. Generating synonyms
      1. 2.1. Introduction to synonym expansion
      2. 2.2. The importance of context
      3. 2.3. Feed-forward neural networks
      4. 2.4. Using word2vec
      5. 2.5. Evaluations and comparisons
      6. 2.6. Considerations for production systems
      7. Summary
  11. Part 2. Throwing neural nets at a search engine
    1. Chapter 3. From plain retrieval to text generation
      1. 3.1. Information need vs. query: Bridging the gap
      2. 3.2. Learning over sequences
      3. 3.3. Recurrent neural networks
      4. 3.4. LSTM networks for unsupervised text generation
      5. 3.5. From unsupervised to supervised text generation
      6. 3.6. Considerations for production systems
      7. Summary
    2. Chapter 4. More-sensitive query suggestions
      1. 4.1. Generating query suggestions
      2. 4.2. Lucene Lookup APIs
      3. 4.3. Analyzed suggesters
      4. 4.4. Using language models
      5. 4.5. Content-based suggesters
      6. 4.6. Neural language models
      7. 4.7. Character-based neural language model for suggestions
      8. 4.8. Tuning the LSTM language model
      9. 4.9. Diversifying suggestions using word embeddings
      10. Summary
    3. Chapter 5. Ranking search results with word embeddings
      1. 5.1. The importance of ranking
      2. 5.2. Retrieval models
      3. 5.3. Neural information retrieval
      4. 5.4. From word to document vectors
      5. 5.5. Evaluations and comparisons
      6. Summary
    4. Chapter 6. Document embeddings for rankings and recommendations
      1. 6.1. From word to document embeddings
      2. 6.2. Using paragraph vectors in ranking
      3. 6.3. Document embeddings and related content
      4. Summary
  12. Part 3. One step beyond
    1. Chapter 7. Searching across languages
      1. 7.1. Serving users who speak multiple languages
      2. 7.2. Statistical machine translation
      3. 7.3. Working with parallel corpora
      4. 7.4. Neural machine translation
      5. 7.5. Word and document embeddings for multiple languages
      6. Summary
    2. Chapter 8. Content-based image search
      1. 8.1. Image contents and search
      2. 8.2. A look back: Text-based image retrieval
      3. 8.3. Understanding images
      4. 8.4. Deep learning for image representation
      5. 8.5. Working with unlabeled images
      6. Summary
    3. Chapter 9. A peek at performance
      1. 9.1. Performance and the promises of deep learning
      2. 9.2. Indexes and neurons working together
      3. 9.3. Working with streams of data
      4. Summary
      5. Looking forward
  13. Index
  14. List of Figures
  15. List of Tables
  16. List of Listings

Product information

  • Title: Deep Learning for Search
  • Author(s): Tommaso Teofili
  • Release date: June 2019
  • Publisher(s): Manning Publications
  • ISBN: 9781617294792