Next >

Deep Learning and Linguistic Representation

OUTLINE OF THE BOOK FROM ENGINEERING TO COGNITIVE SCIENCE ELEMENTS OF DEEP LEARNING TYPES OF DEEP NEURAL NETWORKS AN EXAMPLE APPLICATION SUMMARY AND CONCLUSIONS Learning Syntactic Structure with Deep Neural Networks SUBJECT-VERB AGREEMENT ARCHITECTURE AND EXPERIMENTS HIERARCHICAL STRUCTURE TREE DNNS SUMMARY AND CONCLUSIONS Machine Learning and the Sentence Acceptability Task GRADIENCE IN SENTENCE ACCEPTABILITY PREDICTING ACCEPTABILITY WITH MACHINE LEARNING MODELS ADDING TAGS AND TREES SUMMARY AND CONCLUSIONS Predicting Human Acceptability Judgements in Context ACCEPTABILITY JUDGEMENTS IN CONTEXT TWO SETS OF EXPERIMENTS THE COMPRESSION EFFECT AND DISCOURSE COHERENCE PREDICTING ACCEPTABILITY WITH DIFFERENT DNN MODELS SUMMARY AND CONCLUSIONS Cognitively Viable Computational Models of Linguistic Knowledge HOW USEFUL ARE LINGUISTIC THEORIES FOR NLP APPLICATIONS?MACHINE LEARNING MODELS VS FORMAL GRAMMAR EXPLAINING LANGUAGE ACQUISITION DEEP LEARNING AND DISTRIBUTIONAL SEMANTICS SUMMARY AND CONCLUSIONS REPRESENTING SYNTACTIC AND SEMANTIC KNOWLEDGE DOMAIN-SPECIFIC LEARNING BIASES AND LANGUAGE ACQUISITION DIRECTIONS FOR FUTURE WORK References Author Index Subject Index

Next >