This thesis addresses questions about early lexical acquisition. Four case studies provide concrete examples of how Bayesian computational modelling can be used to study assumptions about inductive biases, properties of the input data and possible limitations of the learning algorithm.
Table of Contents1. Introduction -- 2. Background -- 3. Particle filters for word segmentation -- 4. Studying the effect of input size for Bayesian word segmentation -- 5. Exploring the role of stress in Bayesian word segmentation -- 6. A joint model of word segmentation and phonological variation -- 7. Conclusion.
"Thesis submitted for the degree of Doctor of Philosophy, Dr. phil. at the Department of Computing, Faculty of Science, Macquarie University, Institut für Computerlinguistik, Neuphilologische Fakultät, Universität Heidelberg" -- title page.
Bibliography: pages 219-232
Awarding InstitutionMacquarie University
Degree TypeThesis PhD
DegreePhD, Macquarie University, Faculty of Science and Engineering, Department of Computing
Department, Centre or SchoolDepartment of Computing
Year of Award2014
Principal SupervisorMark Johnson
Additional Supervisor 1Annette Frank
RightsCopyright Benjamin Börschinger 2014.
Copyright disclaimer: http://mq.edu.au/library/copyright
Extent1 online resource (xvii, 232 pages) graphs, tables