Keywords:
Natural language processing (Computer science).
;
Electronic books.
Type of Medium:
Online Resource
Pages:
1 online resource (338 pages)
Edition:
1st ed.
ISBN:
9789811052095
URL:
https://ebookcentral.proquest.com/lib/geomar/detail.action?docID=5401147
DDC:
006.35
Language:
English
Note:
Intro -- Foreword -- Preface -- Contents -- Contributors -- Acronyms -- 1 A Joint Introduction to Natural Language Processing and to Deep Learning -- 1.1 Natural Language Processing: The Basics -- 1.2 The First Wave: Rationalism -- 1.3 The Second Wave: Empiricism -- 1.4 The Third Wave: Deep Learning -- 1.5 Transitions from Now to the Future -- 1.5.1 From Empiricism to Deep Learning: A Revolution -- 1.5.2 Limitations of Current Deep Learning Technology -- 1.6 Future Directions of NLP -- 1.6.1 Neural-Symbolic Integration -- 1.6.2 Structure, Memory, and Knowledge -- 1.6.3 Unsupervised and Generative Deep Learning -- 1.6.4 Multimodal and Multitask Deep Learning -- 1.6.5 Meta-learning -- 1.7 Summary -- References -- 2 Deep Learning in Conversational Language Understanding -- 2.1 Introduction -- 2.2 A Historical Perspective -- 2.3 Major Language Understanding Tasks -- 2.3.1 Domain Detection and Intent Determination -- 2.3.2 Slot Filling -- 2.4 Elevating State of the Art: From Statistical Modeling to Deep Learning -- 2.4.1 Domain Detection and Intent Determination -- 2.4.2 Slot Filling -- 2.4.3 Joint Multitask Multi-domain Modeling -- 2.4.4 Understanding in Context -- 2.5 Summary -- References -- 3 Deep Learning in Spoken and Text-Based Dialog Systems -- 3.1 Introduction -- 3.2 Learning Methodology for Components of a Dialog System -- 3.2.1 Discriminative Methods -- 3.2.2 Generative Methods -- 3.2.3 Decision-Making -- 3.3 Goal-Oriented Neural Dialog Systems -- 3.3.1 Neural Language Understanding -- 3.3.2 Dialog State Tracker -- 3.3.3 Deep Dialog Manager -- 3.4 Model-Based User Simulators -- 3.5 Natural Language Generation -- 3.6 End-to-End Deep Learning Approaches to Building Dialog Systems -- 3.7 Deep Learning for Open Dialog Systems -- 3.8 Datasets for Dialog Modeling -- 3.8.1 The Carnegie Mellon Communicator Corpus.
,
3.8.2 ATIS-Air Travel Information System Pilot Corpus -- 3.8.3 Dialog State Tracking Challenge Dataset -- 3.8.4 Maluuba Frames Dataset -- 3.8.5 Facebook's Dialog Datasets -- 3.8.6 Ubuntu Dialog Corpus -- 3.9 Open Source Dialog Software -- 3.10 Dialog System Evaluation -- 3.11 Summary -- References -- 4 Deep Learning in Lexical Analysis and Parsing -- 4.1 Background -- 4.2 Typical Lexical Analysis and Parsing Tasks -- 4.2.1 Word Segmentation -- 4.2.2 POS Tagging -- 4.2.3 Syntactic Parsing -- 4.2.4 Structured Predication -- 4.3 Structured Prediction Methods -- 4.3.1 Graph-Based Methods -- 4.3.2 Transition-Based Methods -- 4.4 Neural Graph-Based Methods -- 4.4.1 Neural Conditional Random Fields -- 4.4.2 Neural Graph-Based Dependency Parsing -- 4.5 Neural Transition-Based Methods -- 4.5.1 Greedy Shift-Reduce Dependency Parsing -- 4.5.2 Greedy Sequence Labeling -- 4.5.3 Globally Optimized Models -- 4.6 Summary -- References -- 5 Deep Learning in Knowledge Graph -- 5.1 Introduction -- 5.1.1 Basic Concepts -- 5.1.2 Typical Knowledge Graphs -- 5.2 Knowledge Representation Learning -- 5.3 Neural Relation Extraction -- 5.3.1 Sentence-Level NRE -- 5.3.2 Document-Level NRE -- 5.4 Bridging Knowledge with Text: Entity Linking -- 5.4.1 The Entity Linking Framework -- 5.4.2 Deep Learning for Entity Linking -- 5.5 Summary -- References -- 6 Deep Learning in Machine Translation -- 6.1 Introduction -- 6.2 Statistical Machine Translation and Its Challenges -- 6.2.1 Basics -- 6.2.2 Challenges in Statistical Machine Translation -- 6.3 Component-Wise Deep Learning for Machine Translation -- 6.3.1 Deep Learning for Word Alignment -- 6.3.2 Deep Learning for Translation Rule Probability Estimation -- 6.3.3 Deep Learning for Reordering Phrases -- 6.3.4 Deep Learning for Language Modeling -- 6.3.5 Deep Learning for Feature Combination.
,
6.4 End-to-End Deep Learning for Machine Translation -- 6.4.1 The Encoder-Decoder Framework -- 6.4.2 Neural Attention in Machine Translation -- 6.4.3 Addressing Technical Challenges of Large Vocabulary -- 6.4.4 End-to-End Training to Optimize Evaluation Metric Directly -- 6.4.5 Incorporating Prior Knowledge -- 6.4.6 Low-Resource Language Translation -- 6.4.7 Network Structures in Neural Machine Translation -- 6.4.8 Combination of SMT and NMT -- 6.5 Summary -- References -- 7 Deep Learning in Question Answering -- 7.1 Introduction -- 7.2 Deep Learning in Question Answering over Knowledge Base -- 7.2.1 The Information Extraction Style -- 7.2.2 The Semantic Parsing Style -- 7.2.3 The Information Extraction Style Versus the Semantic Parsing Style -- 7.2.4 Datasets -- 7.2.5 Challenges -- 7.3 Deep Learning in Machine Comprehension -- 7.3.1 Task Description -- 7.3.2 Feature Engineering-Based Methods in Machine Comprehension -- 7.3.3 Deep Learning Methods in Machine Comprehension -- 7.4 Summary -- References -- 8 Deep Learning in Sentiment Analysis -- 8.1 Introduction -- 8.2 Sentiment-Specific Word Embedding -- 8.3 Sentence-Level Sentiment Classification -- 8.3.1 Convolutional Neural Networks -- 8.3.2 Recurrent Neural Networks -- 8.3.3 Recursive Neural Networks -- 8.3.4 Integration of External Resources -- 8.4 Document-Level Sentiment Classification -- 8.5 Fine-Grained Sentiment Analysis -- 8.5.1 Opinion Mining -- 8.5.2 Targeted Sentiment Analysis -- 8.5.3 Aspect-Level Sentiment Analysis -- 8.5.4 Stance Detection -- 8.5.5 Sarcasm Recognition -- 8.6 Summary -- References -- 9 Deep Learning in Social Computing -- 9.1 Introduction to Social Computing -- 9.2 Modeling User-Generated Content with Deep Learning -- 9.2.1 Traditional Semantic Representation Approaches -- 9.2.2 Semantic Representation with Shallow Embedding.
,
9.2.3 Semantic Representation with Deep Neural Networks -- 9.2.4 Enhancing Semantic Representation with Attention Mechanism -- 9.3 Modeling Social Connections with Deep Learning -- 9.3.1 Social Connections on Social Media -- 9.3.2 A Network Representation Learning Approach to Modeling Social Connections -- 9.3.3 Shallow Embedding Based Models -- 9.3.4 Deep Neural Network Based Models -- 9.3.5 Applications of Network Embedding -- 9.4 Recommendation with Deep Learning -- 9.4.1 Recommendation on Social Media -- 9.4.2 Traditional Recommendation Algorithms -- 9.4.3 Shallow Embedding Based Models -- 9.4.4 Deep Neural Network Based Models -- 9.5 Summary -- References -- 10 Deep Learning in Natural Language Generation from Images -- 10.1 Introduction -- 10.2 Background -- 10.3 Deep Learning Frameworks to Generate Natural Language from an Image -- 10.3.1 The End-to-End Framework -- 10.3.2 The compositional framework -- 10.3.3 Other Frameworks -- 10.4 Evaluation Metrics and Benchmarks -- 10.5 Industrial Deployment of Image Captioning -- 10.6 Examples: Natural Language Descriptions of Images -- 10.7 Recent Research on Generating Stylistic Natural Language from Images -- 10.8 Summary -- References -- 11 Epilogue: Frontiers of NLP in the Deep Learning Era -- 11.1 Introduction -- 11.2 Two New Perspectives -- 11.2.1 The Task-Centric Perspective -- 11.2.2 The Representation-Centric Perspective -- 11.3 Major Recent Advances in Deep Learning for NLP and Research Frontiers -- 11.3.1 Compositionality for Generalization -- 11.3.2 Unsupervised Learning for NLP -- 11.3.3 Reinforcement Learning for NLP -- 11.3.4 Meta-Learning for NLP -- 11.3.5 Interpretability: Weak-Sense and Strong-Sense -- 11.4 Summary -- References -- Appendix Glossary.
Permalink