Deep Learning and Linguistic Representation

The application of deep learning methods to problems in natural language processing has generated significant progress across a wide range of natural language processing tasks. For some of these applications, deep learning models now approach or surpass human performance. While the success of this approach has transformed the engineering methods of machine learning in artificial intelligence, the significance of these achievements for the modelling of human learning and representation remains unclear.
Deep Learning and Linguistic Representation looks at the application of a variety of deep learning systems to several cognitively interesting NLP tasks. It also considers the extent to which this work illuminates our understanding of the way in which humans acquire and represent linguistic knowledge.
Key Features:
combines an introduction to deep learning in AI and NLP with current research on Deep Neural Networks in computational linguistics.
is self-contained and suitable for teaching in computer science, AI, and cognitive science courses; it does not assume extensive technical training in these areas.
provides a compact guide to work on state of the art systems that are producing a revolution across a range of difficult natural language tasks.

Shalom Lappin is Professor of Natural Language Processing at Queen Mary University of London, Professor of Computational Linguistics at the University of Gothenburg and Emeritus Professor of Computational Linguistics at King's College London.

Chapter 1 Introduction: Deep Learning in Natural Language Processing 1.1 OUTLINE OF THE BOOK 1.2 FROM ENGINEERING TO COGNITIVE SCIENCE 1.3 ELEMENTS OF DEEP LEARNING 1.4 TYPES OF DEEP NEURAL NETWORKS 1.5 AN EXAMPLE APPLICATION 1.6 SUMMARY AND CONCLUSIONS Chapter 2 Learning Syntactic Structure with Deep Neural Networks 2.1 SUBJECT-VERB AGREEMENT 2.2 ARCHITECTURE AND EXPERIMENTS 2.3 HIERARCHICAL STRUCTURE 2.4 TREE DNNS 2.5 SUMMARY AND CONCLUSIONS Chapter 3 Machine Learning and The Sentence Acceptability Task 3.1 GRADIENCE IN SENTENCE ACCEPTABILITY 3.2 PREDICTING ACCEPTABILITY WITH MACHINE LEARNING MODELS 3.3 ADDING TAGS AND TREES 3.4 SUMMARY AND CONCLUSIONS Chapter 4 Predicting Human Acceptability Judgments in Context 4.1 ACCEPTABILITY JUDGMENTS IN CONTEXT 4.2 TWO SETS OF EXPERIMENTS 4.3 THE COMPRESSION EFFECT AND DISCOURSE COHERENCE 4.4 PREDICTING ACCEPTABILITY WITH DIFFERENT DNN MODELS 4.5 SUMMARY AND CONCLUSIONS Chapter 5 Cognitively Viable Computational Models of Linguistic Knowledge 5.1 HOW USEFUL ARE LINGUISTIC THEORIES FOR NLP APPLICATIONS? 5.2 MACHINE LEARNING MODELS VS FORMAL GRAMMAR 5.3 EXPLAINING LANGUAGE ACQUISITION 5.4 DEEP LEARNING AND DISTRIBUTIONAL SEMANTICS 1 5.5 SUMMARY AND CONCLUSIONS Chapter 6 Conclusions and Future Work 6.1 REPRESENTING SYNTACTIC AND SEMANTIC KNOWLEDGE 6.2 DOMAIN SPECIFIC LEARNING BIASES AND LANGUAGE ACQUISITION 6.3 DIRECTIONS FOR FUTURE WORK REFERENCES Author Index Subject Index