Deep Learning and Linguistic Representation
OUTLINE OF THE BOOKFROM ENGINEERING TO COGNITIVE SCIENCEELEMENTS OF DEEP LEARNINGTYPES OF DEEP NEURAL NETWORKSAN EXAMPLE APPLICATIONSUMMARY AND CONCLUSIONSLearning Syntactic Structure with Deep Neural NetworksSUBJECT-VERB AGREEMENTARCHITECTURE AND EXPERIMENTSHIERARCHICAL STRUCTURETREE DNNSSUMMARY AND CONCLUSIONSMachine Learning and the Sentence Acceptability TaskGRADIENCE IN SENTENCE ACCEPTABILITYPREDICTING ACCEPTABILITY WITH MACHINE LEARNING MODELSADDING TAGS AND TREESSUMMARY AND CONCLUSIONSPredicting Human Acceptability Judgements in ContextACCEPTABILITY JUDGEMENTS IN CONTEXTTWO SETS OF EXPERIMENTSTHE COMPRESSION EFFECT AND DISCOURSE COHERENCEPREDICTING ACCEPTABILITY WITH DIFFERENT DNN MODELSSUMMARY AND CONCLUSIONSCognitively Viable Computational Models of Linguistic KnowledgeHOW USEFUL ARE LINGUISTIC THEORIES FOR NLP APPLICATIONS?MACHINE LEARNING MODELS VS FORMAL GRAMMAREXPLAINING LANGUAGE ACQUISITIONDEEP LEARNING AND DISTRIBUTIONAL SEMANTICSSUMMARY AND CONCLUSIONSREPRESENTING SYNTACTIC AND SEMANTIC KNOWLEDGEDOMAIN-SPECIFIC LEARNING BIASES AND LANGUAGE ACQUISITIONDIRECTIONS FOR FUTURE WORKReferencesAuthor IndexSubject Index
