Computing meaning . Volume 4 / / Harry Bunt, Johan Bos, Stephen Pulman, editors

• Record Nr.: UNINA9910299038703321
• Pubbl/distr/stampa: Dordrecht, Netherlands : , : Springer, , 2014
• ISBN: 94-007-7284-X
• Edizione: [1st ed. 2014.]
• Descrizione fisica: 1 online resource (viii, 260 pages) : illustrations
• Collana: Text, Speech and Language Technology, , 1386-291X ; ; 47
• Disciplina: 401.430285
• Soggetti: Semantics - Data processing; Formal languages - Semantics
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: "ISSN: 1386-291X."
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Computing Meaning: Annotation, Representation, and Inference by Harry Bunt, Johan Bos, and Stephen Pulman -- Part I Semantic Representation and Compositionality . Deterministic Statistical Mapping of Sentences to Underspecified Semantics by Hiyan Alshawi, Pi-Chuan Chang, and Michael Ringgaard -- A formal approach to linking logical form and vector-space lexical semantics by Dan Garrette, Katrin Erk, and Raymond Mooney -- Annotations that effectively contribute to semantic interpretation by Harry Bunt -- Concrete Sentence Spaces for Compositional Distributional Models of Meaning by Edward Grefenstette, Mehmoosh Sadrzadeh, Stephen Clark, Bob Coecke, and Stephen Pulman -- Part II Inference and Understanding . Recognizing Textual Entailment and Computational Semantics by Johan Bos -- Abductive Reasoning with a Large Knowledge Base for Discourse Processing by Ekaterina Ovchinnikova, Niloofar Montazeri, Theodore Alexandrov, Jerry R. Hobbs, Michael C. McCord, and Rutu Mulkar-Mehta -- Natural logic and natural language inference by Bill MacCartney and Christopher D. Manning -- Designing Efficient Controlled Languages for Ontologies by Camilo Thorne, Raffaella Bernardi, and Diego Calvanese -- Part III Semantic Resources and Annotation . A Context-Change Semantics for Dialogue Acts by Harry Bunt -- VerbNet Class Assignment as a WSD Task by Susan Windisch Brown, Dmitriy Dligach and Martha Palmer -- Annotation of Compositional Operations with GLML by Pustejovsky, Rumshisky, Batiukova, and Moszkowicz -- ; Incremental Recognition and Prediction of Dialogue Acts by Volha Petukhova and Harry Bunt -- Index .
• Sommario/riassunto: This book is a collection of papers by leading researchers in computational semantics. It presents a state-of-the-art overview of recent and current research in computational semantics, including descriptions of new methods for constructing and improving resources for semantic computation, such as WordNet, VerbNet, and semantically annotated corpora. It also presents new statistical methods in semantic computation, such as the application of distributional semantics in the compositional calculation of sentence meanings. Computing the meaning of sentences, texts, and spoken or texted dialogue is the ultimate challenge in natural language processing, and the key to a wide range of exciting applications. The breadth and depth of coverage of this book makes it suitable as a reference and overview of the state of the field for researchers in Computational Linguistics, Semantics, Computer Science, Cognitive Science, and Artificial Intelligence.

Self-adaptive systems for machine intelligence [[electronic resource] /] / Haibo He

• Record Nr.: UNINA9910830087803321
• Autore: He Haibo <1976->
• Pubbl/distr/stampa: Hoboken, N.J., : Wiley-Interscience, 2011
• ISBN: 1-283-17569-X; 9786613175694; 1-118-02559-8; 1-118-02560-1; 1-118-02558-X
• Descrizione fisica: 1 online resource (248 p.)
• Classificazione: COM044000
• Disciplina: 006.3/1; 006.31
• Soggetti: Machine learning; Self-organizing systems; Artificial intelligence
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: Description based upon print version of record.
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: SELF-ADAPTIVE SYSTEMS FOR MACHINE INTELLIGENCE; CONTENTS; Preface; Acknowledgments; 1 Introduction; 1.1 The Machine Intelligence Research; 1.2 The Two-Fold Objectives: Data-Driven and Biologically Inspired Approaches; 1.3 How to Read This Book; 1.3.1 Part I: Data-Driven Approaches for Machine Intelligence (Chapters 2, 3, and 4); 1.3.2 Part II: Biologically-Inspired Approaches for Machine Intelligence (Chapters 4, 5, and 6); 1.4 Summary and Further Reading; References; 2 Incremental Learning; 2.1 Introduction; 2.2 Problem Foundation; 2.3 An Adaptive Incremental Learning Framework; 2.4 Design of the Mapping Function2.4.1 Mapping Function Based on Euclidean Distance; 2.4.2 Mapping Function Based on Regression Learning Model; 2.4.3 Mapping Function Based on Online Value System; 2.4.3.1 A Three-Curve Fitting (TCF) Technique; 2.4.3.2 System-Level Architecture for Online Value Estimation; 2.5 Case Study; 2.5.1 Incremental Learning from Video Stream; 2.5.1.1 Feature Representation; 2.5.1.2 Experimental Results; 2.5.1.3 Concept Drifting Issue in Incremental Learning; 2.5.2 Incremental Learning for Spam E-mail Classification; 2.5.2.1 Data Set Characteristic and System Configuration2.5.2.2 Simulation Results; 2.6 Summary; References; 3 Imbalanced Learning; 3.1 Introduction; 3.2 The Nature of Imbalanced Learning; 3.3 Solutions for Imbalanced Learning; 3.3.1 Sampling Methods for Imbalanced Learning; 3.3.1.1 Random Oversampling and Undersampling; 3.3.1.2 Informed Undersampling; 3.3.1.3 Synthetic Sampling with Data Generation; 3.3.1.4 Adaptive Synthetic Sampling; 3.3.1.5 Sampling with Data Cleaning Techniques; 3.3.1.6 Cluster-Based Sampling Method; 3.3.1.7 Integration of Sampling and Boosting; 3.3.2 Cost-Sensitive Methods for Imbalanced Learning3.3.2.1 Cost-Sensitive Learning Framework; 3.3.2.2 Cost-Sensitive Data Space Weighting with Adaptive Boosting; 3.3.2.3 Cost-Sensitive Decision Trees; 3.3.2.4 Cost-Sensitive Neural Networks; 3.3.3 Kernel-Based Methods for Imbalanced Learning; 3.3.3.1 Kernel-Based Learning Framework; 3.3.3.2 Integration of Kernel Methods with Sampling Methods; 3.3.3.3 Kernel Modification Methods for Imbalanced Learning; 3.3.4 Active Learning Methods for Imbalanced Learning; 3.3.5 Additional Methods for Imbalanced Learning; 3.4 Assessment Metrics for Imbalanced Learning3.4.1 Singular Assessment Metrics; 3.4.2 Receiver Operating Characteristics (ROC) Curves; 3.4.3 Precision-Recall (PR) Curves; 3.4.4 Cost Curves; 3.4.5 Assessment Metrics for Multiclass Imbalanced Learning; 3.5 Opportunities and Challenges; 3.6 Case Study; 3.6.1 Nonlinear Normalization; 3.6.2 Data Sets Distribution; 3.6.3 Simulation Results and Discussions; 3.7 Summary; References; 4 Ensemble Learning; 4.1 Introduction; 4.2 Hypothesis Diversity; 4.2.1 Q-Statistics; 4.2.2 Correlation Coefficient; 4.2.3 Disagreement Measure; 4.2.4 Double-Fault Measure
• Sommario/riassunto: "This book will advance the understanding and application of self-adaptive intelligent systems; therefore it will potentially benefit the long-term goal of replicating certain levels of brain-like intelligence in complex and networked engineering systems. It will provide new approaches for adaptive systems within uncertain environments. This will provide an opportunity to evaluate the strengths and weaknesses of the current state-of-the-art of knowledge, give rise to new research directions, and educate future professionals in this domain. Self-adaptive intelligent systems have wide applications from military ; security systems to civilian daily life. In this book, different application problems, including pattern recognition, classification, image recovery, and sequence learning, will be presented to show the capability of the proposed systems in learning, memory, and prediction. Therefore, this book will also provide potential new solutions to many real-world applications"--; "This book will advance the understanding and application of self-adaptive intelligent systems; therefore it will potentially benefit the long-term goal of replicating certain levels of brain-like intelligence in complex and networked engineering systems. It will provide new approaches for adaptive systems within uncertain environments. This will provide an opportunity to evaluate the strengths and weaknesses of the current state-of-the-art of knowledge, give rise to new research directions, and educate future professionals in this domain"--