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.

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.

Addresses a central problem in cognitive science, concerning the learning procedures through which humans acquire and represent natural language. Brings together world leading scholars from a range of disciplines, includingcomputational linguistics, psychology, behavioural science, and mathematical linguistics. Will appeal to researchers in computational and mathematical linguistics, psychology and behavioral science, AI and NLP. Represents a wide spectrum of perspectives

This volume contains essays on ellipsis -- the omission of understood words or grammatical items from a sentence -- and the closely related syntactic phenomena of conjunction and gapping. Ellipsis poses interesting challenges for linguists because speakers are expressing something that is not present in their words. This volume not only addresses the three perspectives resulting from recent research -- Chomsky's syntactic Government and Binding approach, the semantic theories, and the processing accounts -- but it also examines the cross-linguistic aspects of ellipsis by comparing the possibilities for a given type of elided structure in Japanese, Arabic, Hebrew, and in English. This volume will be of interest to both semanticists and syntacticians.

The book offers a detailed critique of the economy-of-derivation model of grammar that has emerged within the framework of Chomsky's Minimalist Program. It looks at the conceptual and computational complexity problems as well as the empirical consequences of both global and local economy principles. The book compares the economy-of-derivation model with a local constraint model of grammar that does not invoke conditions on sets of derivations or on possible operations in a derivation. It argues that the pure local constraint model of grammar avoids the complexity problems resulting from economy-of-derivation principles and provides a more satisfactory explanation of the linguistic facts that economy theorists have cited in support of their approach. The local constraint model also allows for a more natural and empirically well-motivated grammatical architecture than the one postulated by the Minimalist Program.