© 2019

Developing Enterprise Chatbots

Learning Linguistic Structures


Table of contents

  1. Front Matter
    Pages i-xv
  2. Boris Galitsky
    Pages 1-11
  3. Boris Galitsky
    Pages 13-51
  4. Boris Galitsky, Saveli Goldberg
    Pages 53-83
  5. Boris Galitsky
    Pages 121-162
  6. Boris Galitsky
    Pages 221-252
  7. Boris Galitsky
    Pages 253-326
  8. Boris Galitsky
    Pages 365-426
  9. Boris Galitsky
    Pages 427-463
  10. Boris Galitsky
    Pages 533-555
  11. Boris Galitsky
    Pages 557-559

About this book


A chatbot is expected to be capable of supporting a cohesive and coherent conversation and be knowledgeable, which makes it one of the most complex intelligent systems being designed nowadays. Designers have to learn to combine intuitive, explainable language understanding and reasoning approaches with high-performance statistical and deep learning technologies.  

Today, there are two popular paradigms for chatbot construction:

1.     Build a bot platform with universal NLP and ML capabilities so that a bot developer  for a particular enterprise, not being an expert, can populate it with training data;

2.    Accumulate a huge set of training dialogue data, feed it to a deep learning network and expect the trained chatbot to automatically learn “how to chat”. 

Although these two approaches are reported to imitate some intelligent dialogues, both of them are unsuitable for enterprise chatbots, being unreliable and too brittle.

The latter approach is based on a belief that some learning miracle will happen and a chatbot will start functioning without a thorough feature and domain engineering by an expert and interpretable dialogue management algorithms.

Enterprise high-performance chatbots with extensive domain knowledge require a mix of statistical, inductive, deep machine learning and learning from the web, syntactic, semantic and discourse NLP, ontology-based reasoning and a state machine to control a dialogue. This book will provide a comprehensive source of algorithms and architectures for building chatbots for various domains based on the recent trends in computational linguistics and machine learning. The foci of this book are applications of discourse analysis in text relevant assessment, dialogue management and content generation, which help to overcome the limitations of platform-based and data driven-based approaches.

Supplementary material and code is available at


dialogue management for chatbots search engineering linguistic support ontologies for chatbots rhetorical analysis

Authors and affiliations

  1. 1.Oracle (United States)San JoseUSA

About the authors

Dr. Boris Galitsky has contributed linguistic and machine learning technologies to Silicon Valley startups for the last 25 years, as well as eBay and Oracle, where he is currently an architect of a digital assistant project. An author of two computer science books, 150+ publications and 15+ patents, he is now researching how discourse analysis improves search relevance and supports dialogue management. In his previous book, Dr. Galitsky presented a foundation of autistic reasoning which shed a light on how chatbots should facilitate conversations. Boris is an Apache committer to OpenNLP where he created the OpenNLP.Similarity component that is a basis for chatbot development.

Bibliographic information

Industry Sectors
Chemical Manufacturing
IT & Software
Consumer Packaged Goods
Materials & Steel
Finance, Business & Banking
Energy, Utilities & Environment
Oil, Gas & Geosciences