We use connectionist modeling to develop an analysis of stress systems in terms of ease of learnability. In traditional linguistic analyses, learnability arguments determine default parameter settings based on the feasibilty of logically deducing correct settings from an initial state. Our approach provides an empirical alternative to such arguments. Based on perceptron learning experiments using data from nineteen human languages, we develop a novel characterization of stress patterns in terms of six parameters. These provide both a partial description of the stress pattern itself and a prediction of its learnability, without invoking abstract theoretical constructs such as metrical feet. This work demonstrates that machine learning methods can provide a fresh approach to understanding linguistic phenomena.
[1]
J. Oxford,et al.
Oxford
,
1968,
Leaving The Arena.
[2]
B. Hayes.
A metrical theory of stress rules
,
1980
.
[3]
Geoffrey E. Hinton,et al.
Learning internal representations by error propagation
,
1986
.
[4]
J. Goldsmith.
Autosegmental and Metrical Phonology
,
1990
.
[5]
B. Dresher,et al.
A computational learning model for metrical phonology
,
1990,
Cognition.
[6]
David S. Touretzky,et al.
What a Perceptron Reveals about Metrical Phonology
,
1991
.