Details
Developing Enterprise Chatbots
Learning Linguistic Structures|
85,59 € |
|
| Verlag: | Springer |
| Format: | |
| Veröffentl.: | 04.04.2019 |
| ISBN/EAN: | 9783030042998 |
| Sprache: | englisch |
Dieses eBook enthält ein Wasserzeichen.
Beschreibungen
<p>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. </p><p>Today, there are two popular paradigms for chatbot construction:</p><p>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;</p><p>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”. </p><p>Although these two approaches are reported to imitate some intelligent dialogues, both of them are unsuitable for enterprise chatbots, being unreliable and too brittle.</p><p>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.</p><p>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.</p><p>Supplementary material and code is available at https://github.com/bgalitsky/relevance-based-on-parse-trees <br></p>
Introduction to Chatbots.- Social Chatbots and Development Platforms.- Chatbot Components and Architectures.- Providing Natural Language Access to a Database.- Chatbot Relevance at Syntactic Level.- Semantic Skeleton-based Search for Question and Answering Chatbots.- Relevance at the Level of Paragraph: Parse Thickets.- Chatbot Thesauri.- Content Processing Pipeline.- Achieving Rhetoric Agreement in a Conversation.- Discourse-level Dialogue Management,- Chatbots Providing and Accepting Argumentation.
<b>Dr. Boris Galitsky</b> 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.
<p>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. </p><p>Today, there are two popular paradigms for chatbot construction:</p>
<p>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;</p>
<p>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”. </p>
<p>Although these two approaches are reported to imitate some intelligent dialogues, both of them are unsuitable for enterprise chatbots, being unreliableand too brittle.</p>
<p>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.</p>
<p>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.</p><p>Supplementary material and code is available at https://github.com/bgalitsky/relevance-based-on-parse-trees<br></p>
<p>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;</p>
<p>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”. </p>
<p>Although these two approaches are reported to imitate some intelligent dialogues, both of them are unsuitable for enterprise chatbots, being unreliableand too brittle.</p>
<p>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.</p>
<p>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.</p><p>Supplementary material and code is available at https://github.com/bgalitsky/relevance-based-on-parse-trees<br></p>
Easy to follow with an intuitive introduction to a number of modern, state-of-the-art AI techniques, from language understanding to dialogue management Comprehensive code snippets are provided, along with complete open source code as an Apache project, multiple components to choose from and integrate with, available for download Fosters a deep understanding of AI through the prism of chatbot features. Will take you far beyond the deep learning- based and intent recognition-based approaches popular today Dispels the myth that an industrial chatbot can be built in a short period of time by a non expert, relying on a platform or on a universal learning framework where a large enough amount of data suffices to conduct a dialogue
Diese Produkte könnten Sie auch interessieren:
