Learnability and Markedness in Data-Driven Acquisition of Stress

This paper investigates the computational grounding of learning theories developed within a metrical phonology approach to stress assignment. In current research, the Principles and Parameters approach to learning stress is pervasive. We point out some inherent problems associated with this approach in learning the stress system of a particular language by setting parameters (the case of Dutch), which is shown to be an inherently noisy problem. The paper focuses on two aspects of this problem: we empirically examine the eeect of input encodings on learnability, and we investigate the possibility of a data-oriented approach as an alternative to the principles and parameters approach. We show that data-oriented similarity-based machine learning techniques like Backpropagation Learning, Instance-Based Learning and Analogical Modeling working on phonemic input encodings (i) are able to learn metrical phonology abstractions based on concepts like syllable weight, (ii) that their performance can be related to various degrees of markedness of metrical phenomena, and (iii) that in addition, they are able to extract generalizations which cannot be expressed within the metrical framework without recourse to lexical marking. We also provide a quantitative comparison of the performance of the three algorithms investigated.