Yan Huang

Although deep learning models have achieved great progress in vision, speech, language, planning, control, and many other areas, there still exists a large performance gap between deep learning models and the human cognitive system. Many researchers argue that one of the major reasons accounting for the performance gap is that deep learning models and the human cognitive system process visual information in very different ways. To mimic the performance gap, since 2014, there has been a trend to model various cognitive mechanisms from cognitive neuroscience, e.g., attention, memory, reasoning, and decision, based on deep learning models. This book unifies these new kinds of deep learning models and calls them deep cognitive networks, which model various human cognitive mechanisms based on deep learning models. As a result, various cognitive functions are implemented, e.g., selective extraction, knowledge reuse, and problem solving, for more effective information processing. This book first summarizes existing evidence of human cognitive mechanism modeling from cognitive psychology and proposes a general framework of deep cognitive networks that jointly considers multiple cognitive mechanisms. Then, it analyzes related works and focuses primarily but not exclusively, on the taxonomy of four key cognitive mechanisms (i.e., attention, memory, reasoning, and decision) surrounding deep cognitive networks. Finally, this book studies two representative cases of applying deep cognitive networks to the task of image-text matching and discusses important future directions.

This dictionary provides a full and authoritative guide to the meanings of the terms, concepts, and theories employed in pragmatics. Pragmatics is a central subject in linguistics and philosophy and an increasingly important topic in fields such as cognitive science, informatics, artificial intelligence, neuroscience, and pathology. Its rapid development has produced new theories, methods, approaches, and schools of thought. These in turn have resulted in a vast vocabulary of new terms and in modified meanings for existing terms. Such terms help advance research and facilitate discussion, but they can also cause confusion and act as barriers to understanding and communication. Yan Huang defines and explains them all, from the most traditional to the most recent. Covering every branch of research and all theoretical approaches and with the needs of students and researchers firmly in mind he writes each entry in the simplest possible terms for the subject in question, gives references to relevant seminal and recent work, provides numerous cross-references to related entries, and shows how each term and concept is applied and used in different contexts. Written by one of the leading experts in the field, Professor Huang's dictionary will be a much valued resource for students and researchers in every aspect of the field.

Yan Huang's highly successful textbook on pragmatics - the study of language in use - has been fully revised and updated in this second edition. It includes a brand new chapter on reference, a major topic in both linguistics and the philosophy of language. Chapters have also been updated to include new material on upward and downward entailment, current debates about conversational implicature, impoliteness, emotional deixis, contextualism versus semantic minimalism, and the elimination of binding conditions. The book draws on data from English and a wide range of the world's languages, and shows how pragmatics is related to the study of semantics, syntax, and sociolinguistics and to such fields as the philosophy of language, linguistic anthropology, and artificial intelligence. Professor Huang includes exercises and essay topics at the end of each chapter, and offers guidance and suggested solutions at the end of the volume. Written by one of the leading scholars in the field, this new edition will continue to be an ideal textbook for students of linguistics, and a valuable resource for scholars and students of language in philosophy, psychology, anthropology, and computer science.

This dictionary provides a full and authoritative guide to the meanings of the terms, concepts, and theories employed in pragmatics, the study of language in use. Pragmatics is a central subject in linguistics and philosophy and an increasingly important topic in fields such as cognitive science, informatics, artificial intelligence, neuroscience, and pathology. Its rapid development has produced new theories, methods, approaches, and schools of thought. These in turn have resulted in a vast vocabulary of new terms and in modified meanings for existing terms. Such terms help advance research and facilitate discussion, but they can also cause confusion and act as barriers to understanding and communication. Yan Huang defines and explains them all, from the most traditional to the most recent. Covering every branch of research and all theoretical approaches and with the needs of students and researchers firmly in mind he writes each entry in the simplest possible terms for the subject in question, gives references to relevant seminal and recent work, provides numerous cross-references to related entries, and shows how each term and concept is applied and used in different contexts. Written by one of the leading experts in the field, Professor Huang's dictionary, the first of its kind ever published, will be a much valued resource for students and researchers in every aspect of the field.

This book develops a pragmatic theory of anaphora within the neo-Gricean framework of conversational implicature. Chomsky claims that anaphora reflects underlying principles of innate Universal Grammar, and the view is widely held that only syntactic and semantic factors are crucial to intrasentential anaphora. Yan Huang questions the basis of the Government and Binding approach and argues that syntax and pragmatics are interconnected in determining many anaphoric processes. Furthermore, he proposes that the extent to which syntax and pragmatics interact varies typologically. There exists a class of language (such as Chinese, Japanese and Korean) in which pragmatics play a central role that in familiar European languages is alleged to be played by grammar. Yan Huang's pragmatic theory has far reaching implications for this important issue in theoretical linguistics.

Understanding any communication depends on the listener or reader recognizing that some words refer to what has already been said or written (his, its, he, there, etc.). This mode of reference, anaphora, involves complicated cognitive and syntactic processes, which people usually perform unerringly, but which present formidable problems for the linguist and cognitive scientist trying to explain precisely how comprehension is achieved. Anaphora is thus a central research focus in syntactic and semantic theory, while understanding and modelling its operation in discourse are important targets in computational linguistics and cognitive science. Yan Huang provides an extensive and accessible overview of the major contemporary issues surrounding anaphora and gives a critical survey of the many and diverse contemporary approaches to it. He provides by far the fullest cross-linguistic account yet published: Dr Huang's survey and analysis are based on a rich collection of data drawn from around 550 of the world's languages. Topics covered include binding and control, null subjects and objects, long distance reflexivisation, logophoricity, bridging-cross reference, switch-reference, and discourse anaphora. Written by a leading expert on anaphora, the book will be the standard point of reference for all those interested in this important topic in theoretical linguistics. It will be a vital reference for advanced undergraduate and graduate courses in syntax, semantics, and pragmatics, on the interfaces between them, on linguistic typology, and on computational linguistics.

Understanding any communication depends on the listener or reader recognizing that some words refer to what has already been said or written (his, its, he, there, etc.). This mode of reference, anaphora, involves complicated cognitive and syntactic processes, which people usually perform unerringly, but which present formidable problems for the linguist and cognitive scientist trying to explain precisely how comprehension is achieved. Anaphora is thus a central research focus in syntactic and semantic theory, while understanding and modelling its operation in discourse are important targets in computational linguistics and cognitive science. Yan Huang provides an extensive and accessible overview of the major contemporary issues surrounding anaphora and gives a critical survey of the many and diverse contemporary approaches to it. He provides by far the fullest cross-linguistic account yet published: Dr Huang's survey and analysis are based on a rich collection of data drawn from around 550 of the world's languages. Topics covered include binding and control, null subjects and objects, long distance reflexivisation, logophoricity, bridging-cross reference, switch-reference, and discourse anaphora. Written by a leading expert on anaphora, the book will be the standard point of reference for all those interested in this important topic in theoretical linguistics. It will be a vital reference for advanced undergraduate and graduate courses in syntax, semantics, and pragmatics, on the interfaces between them, on linguistic typology, and on computational linguistics.