Coverart for item
The Resource Developing Enterprise Chatbots : Learning Linguistic Structures, Boris Galitsky

Developing Enterprise Chatbots : Learning Linguistic Structures, Boris Galitsky

Label
Developing Enterprise Chatbots : Learning Linguistic Structures
Title
Developing Enterprise Chatbots
Title remainder
Learning Linguistic Structures
Statement of responsibility
Boris Galitsky
Creator
Author
Subject
Language
eng
Summary
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 https://github.com/bgalitsky/relevance-based-on-parse-trees
Member of
Cataloging source
EBLCP
http://library.link/vocab/creatorName
Galitsky, Boris
Dewey number
005.75/8
Index
no index present
LC call number
TK5105.884
LC item number
.G35 2019
Literary form
non fiction
Nature of contents
  • dictionaries
  • bibliography
http://library.link/vocab/subjectName
  • Search engines
  • Intelligent agents (Computer software)
  • Generators (Computer programs)
  • Artificial Intelligence.
  • Computational Linguistics.
  • Software Engineering.
Label
Developing Enterprise Chatbots : Learning Linguistic Structures, Boris Galitsky
Instantiates
Publication
Note
4.4.5 Clause Building by Matching the Phrase with Indexed Row
Antecedent source
file reproduced from an electronic resource
Bibliography note
Includes bibliographical references
Carrier category
online resource
Carrier category code
cr
Carrier MARC source
rdacarrier
Content category
text
Content type code
txt
Content type MARC source
rdacontent
Contents
  • Intro; Foreword; Contents; Chapter 1: Introduction; 1.1 Introduction; 1.2 Current Chatbot Trends; 1.3 Current Status of Bot Development; 1.4 How to Read This Book and Build a Chatbot That Can Be Demoed; References; Chapter 2: Chatbot Components and Architectures; 2.1 Introduction to Chatbots Architecture; 2.1.1 Definitions; 2.1.2 Dialogue Manager; 2.1.3 Multimodal Interaction; 2.1.4 Context Tracking; 2.1.5 Topic Detection; 2.1.6 Named Entities and Their Templates; 2.1.7 Information Retrieval; 2.1.8 Personalization; 2.1.9 Architecture of a Task-Oriented Chatbot; 2.2 History of Chatbots
  • 2.3 Deterministic Dialogue Management2.3.1 Handling Context; 2.3.2 Turn-Taking; 2.3.3 Action Selection; 2.3.4 Dialogue Management with Manually Coded RULES; 2.3.5 Finite-State Machines; 2.3.6 Rule-Based Dialogue Management; 2.3.7 Frame and Template-Based Dialogue Management; 2.4 Dialogue Management Based on Statistical Learning; 2.4.1 Bayesian Networks; 2.4.2 Neural Networks; 2.4.3 Markov Models; 2.5 Dialogue Management Based on Example-Based, Active and Transfer Learning; 2.6 Conclusions; References; Chapter 3: Explainable Machine Learning for Chatbots
  • 3.1 What Kind of Machine Learning a Chatbot Needs3.1.1 Accuracy vs Explainability; 3.1.2 Explainable vs Unexplainable Learning; 3.1.3 Use Cases for the ML System Lacking Explainability; 3.1.4 Automated Detection of a Request to Explain; 3.2 Discriminating Between a User Question and User Request; 3.2.1 Examples of Questions and Transactional Requests; 3.2.2 Nearest Neighbor-Based Learning for Questions vs Transactional Requests Recognition; 3.3 A Decision Support Chatbot; 3.3.1 Example of a Decision Support Session; 3.3.2 Computing Decisions with Explanations
  • 3.4 Explanation-Based Learning System Jasmine3.4.1 A Reasoning Schema; 3.4.2 Computing Similarity Between Objects; 3.5 Conclusions; References; Chapter 4: Developing Conversational Natural Language Interface to a Database; 4.1 Introduction; 4.1.1 History; 4.2 Statistical and Deep Learning in NL2SQL Systems; 4.2.1 NL2SQL as Sequence Encoder; 4.2.1.1 Sequence-to-Sequence Model; 4.2.1.2 Sequence-to-Tree Model; 4.2.1.3 Attention Mechanism and Model Training; 4.2.2 Limitations of Neural Network Based Approaches; 4.3 Advancing the State-of-the-Art of NL2SQL
  • 4.3.1 Building NL2SQL via Multiword Mapping4.3.2 Sketch-Based Approach; 4.3.3 Extended Relational Algebra to Handle Aggregation and Nested Query; 4.3.4 Interpreting NL Query via Parse Tree Transformation; 4.3.4.1 Intermediate Representation Language; 4.3.4.2 Mapping the Nodes of Query Parse Tree; 4.4 Designing NL2SQL Based on Recursive Clause Building, Employing Thesauri and Implementing Via Chatbot; 4.4.1 Selecting Deterministic Chatbot-Based Approach; 4.4.2 Interpreting Table.Field Clause; 4.4.3 Collecting Information on a Database and Thesaurus for NL2SQL; 4.4.4 Iterative Clause Formation
Dimensions
unknown
Extent
1 online resource (566 p.)
File format
one file format
Form of item
online
Isbn
9783030042981
Level of compression
unknown
Media category
computer
Media MARC source
rdamedia
Media type code
c
Other control number
10.1007/978-3-030-04299-8
Quality assurance targets
unknown
Reformatting quality
unknown
Specific material designation
remote
System control number
  • on1096537175
  • (OCoLC)1096537175
Label
Developing Enterprise Chatbots : Learning Linguistic Structures, Boris Galitsky
Publication
Note
4.4.5 Clause Building by Matching the Phrase with Indexed Row
Antecedent source
file reproduced from an electronic resource
Bibliography note
Includes bibliographical references
Carrier category
online resource
Carrier category code
cr
Carrier MARC source
rdacarrier
Content category
text
Content type code
txt
Content type MARC source
rdacontent
Contents
  • Intro; Foreword; Contents; Chapter 1: Introduction; 1.1 Introduction; 1.2 Current Chatbot Trends; 1.3 Current Status of Bot Development; 1.4 How to Read This Book and Build a Chatbot That Can Be Demoed; References; Chapter 2: Chatbot Components and Architectures; 2.1 Introduction to Chatbots Architecture; 2.1.1 Definitions; 2.1.2 Dialogue Manager; 2.1.3 Multimodal Interaction; 2.1.4 Context Tracking; 2.1.5 Topic Detection; 2.1.6 Named Entities and Their Templates; 2.1.7 Information Retrieval; 2.1.8 Personalization; 2.1.9 Architecture of a Task-Oriented Chatbot; 2.2 History of Chatbots
  • 2.3 Deterministic Dialogue Management2.3.1 Handling Context; 2.3.2 Turn-Taking; 2.3.3 Action Selection; 2.3.4 Dialogue Management with Manually Coded RULES; 2.3.5 Finite-State Machines; 2.3.6 Rule-Based Dialogue Management; 2.3.7 Frame and Template-Based Dialogue Management; 2.4 Dialogue Management Based on Statistical Learning; 2.4.1 Bayesian Networks; 2.4.2 Neural Networks; 2.4.3 Markov Models; 2.5 Dialogue Management Based on Example-Based, Active and Transfer Learning; 2.6 Conclusions; References; Chapter 3: Explainable Machine Learning for Chatbots
  • 3.1 What Kind of Machine Learning a Chatbot Needs3.1.1 Accuracy vs Explainability; 3.1.2 Explainable vs Unexplainable Learning; 3.1.3 Use Cases for the ML System Lacking Explainability; 3.1.4 Automated Detection of a Request to Explain; 3.2 Discriminating Between a User Question and User Request; 3.2.1 Examples of Questions and Transactional Requests; 3.2.2 Nearest Neighbor-Based Learning for Questions vs Transactional Requests Recognition; 3.3 A Decision Support Chatbot; 3.3.1 Example of a Decision Support Session; 3.3.2 Computing Decisions with Explanations
  • 3.4 Explanation-Based Learning System Jasmine3.4.1 A Reasoning Schema; 3.4.2 Computing Similarity Between Objects; 3.5 Conclusions; References; Chapter 4: Developing Conversational Natural Language Interface to a Database; 4.1 Introduction; 4.1.1 History; 4.2 Statistical and Deep Learning in NL2SQL Systems; 4.2.1 NL2SQL as Sequence Encoder; 4.2.1.1 Sequence-to-Sequence Model; 4.2.1.2 Sequence-to-Tree Model; 4.2.1.3 Attention Mechanism and Model Training; 4.2.2 Limitations of Neural Network Based Approaches; 4.3 Advancing the State-of-the-Art of NL2SQL
  • 4.3.1 Building NL2SQL via Multiword Mapping4.3.2 Sketch-Based Approach; 4.3.3 Extended Relational Algebra to Handle Aggregation and Nested Query; 4.3.4 Interpreting NL Query via Parse Tree Transformation; 4.3.4.1 Intermediate Representation Language; 4.3.4.2 Mapping the Nodes of Query Parse Tree; 4.4 Designing NL2SQL Based on Recursive Clause Building, Employing Thesauri and Implementing Via Chatbot; 4.4.1 Selecting Deterministic Chatbot-Based Approach; 4.4.2 Interpreting Table.Field Clause; 4.4.3 Collecting Information on a Database and Thesaurus for NL2SQL; 4.4.4 Iterative Clause Formation
Dimensions
unknown
Extent
1 online resource (566 p.)
File format
one file format
Form of item
online
Isbn
9783030042981
Level of compression
unknown
Media category
computer
Media MARC source
rdamedia
Media type code
c
Other control number
10.1007/978-3-030-04299-8
Quality assurance targets
unknown
Reformatting quality
unknown
Specific material designation
remote
System control number
  • on1096537175
  • (OCoLC)1096537175

Library Locations

Processing Feedback ...