Josiah Poon - Böcker

This book provides a comprehensive introduction to conversational spoken language understanding and surveys recent advances in conversational AI. It guides the reader through the history, current advancements, and future of natural language understanding (NLU) in human-computer interactions.To this end, the book is structured in seven chapters: Introduction to Natural Language Understanding lays the foundation by tracing the evolution of NLU from early human communication to modern human-computer interactions. Prerequisites and Glossary for Natural Language Understanding then serves as a foundational resource, consolidating essential prerequisites and key terminologies relevant across the book. Single-Turn Natural Language Understanding looks at Single-Turn NLU, focusing on tasks that involve interpreting and processing user inputs in a single interaction, while Multi-Turn Natural Language Understanding moves on systems for extended interactions with users and explores techniques for managing dialogues, using context and integrating external knowledge bases. Next, Evaluating Natural Language Understanding discusses the annotation of datasets and various performance assessment methods, covering different levels of understanding from intent recognition to slot filling and domain classification. Applications and Case Studies in Natural Language Understanding subsequently shows real-world applications of NLU in finance, medicine, and law. Eventually Challenges, Conclusions and Future Directions explores the core obstacles hindering the advancement of NLU, including ambiguity, domain adaptation, data scarcity, and ethical concerns. By understanding these challenges, this chapter highlights the ongoing work needed to advance NLU.This book mainly targets researchers, PhD students, and professionals who are entering this field and look for a state-of-the-art introduction to NLU applied in conversational systems such as chatbots, large language models, or educational systems.

This contributed volume explores how data mining, machine learning, and similar statistical techniques can analyze the types of problems arising from Traditional Chinese Medicine (TCM) research. The book focuses on the study of clinical data and the analysis of herbal data. Challenges addressed include diagnosis, prescription analysis, ingredient discoveries, network based mechanism deciphering, pattern-activity relationships, and medical informatics. Each author demonstrates how they made use of machine learning, data mining, statistics and other analytic techniques to resolve their research challenges, how successful if these techniques were applied, any insight noted and how these insights define the most appropriate future work to be carried out. Readers are given an opportunity to understand the complexity of diagnosis and treatment decision, the difficulty of modeling of efficacy in terms of herbs, the identification of constituent compounds in an herb, the relationship between these compounds and biological outcome so that evidence-based predictions can be made. Drawing on a wide range of experienced contributors, Data Analytics for Traditional Chinese Medicine Research is a valuable reference for professionals and researchers working in health informatics and data mining. The techniques are also useful for biostatisticians and health practitioners interested in traditional medicine and data analytics.

This contributed volume explores how data mining, machine learning, and similar statistical techniques can analyze the types of problems arising from Traditional Chinese Medicine (TCM) research. The book focuses on the study of clinical data and the analysis of herbal data. Challenges addressed include diagnosis, prescription analysis, ingredient discoveries, network based mechanism deciphering, pattern-activity relationships, and medical informatics. Each author demonstrates how they made use of machine learning, data mining, statistics and other analytic techniques to resolve their research challenges, how successful if these techniques were applied, any insight noted and how these insights define the most appropriate future work to be carried out. Readers are given an opportunity to understand the complexity of diagnosis and treatment decision, the difficulty of modeling of efficacy in terms of herbs, the identification of constituent compounds in an herb, the relationship between these compounds and biological outcome so that evidence-based predictions can be made. Drawing on a wide range of experienced contributors, Data Analytics for Traditional Chinese Medicine Research is a valuable reference for professionals and researchers working in health informatics and data mining. The techniques are also useful for biostatisticians and health practitioners interested in traditional medicine and data analytics.