<OT> New Posting: ROA-679

[roa at ruccs.rutgers.edu]

ROA 679-0804

Linear Optimality Theory as a Model of Gradience in Grammar

Frank Keller <keller at inf.ed.ac.uk>

Direct link: http://roa.rutgers.edu/view.php3?roa=679


Abstract:
This paper provides an overview of Linear Optimality Theory
(LOT), a variant of Optimality Theory (OT) designed for
the modeling of gradient acceptability judgment data. We
summarize the empirical properties of gradient data that
have been reported in the experimental literature, and use
them to motivate the design of LOT. We discuss LOT's notions
of constraint competition and optimality, as well as a new
formulation of ranking argumentation, which makes it possible
to apply standard parameter estimation techniques to LOT.
Then the LOT model is compared to Standard OT, to Harmonic
Grammar, and to recently proposed probabilisitic versions of OT.

Comments: To appear in Gisbert Fanselow, Caroline Féry, Ralph Vogel, and Matthias Schlesewsky, eds., Gradience in Grammar: Generative Perspectives. Oxford: Oxford University Press, 2005.
Keywords: gradience, linear OT, cumulativity, harmonic bounding, learnability
Areas: Syntax,Computation,Learnability
Type: Book Chapter

Direct link: http://roa.rutgers.edu/view.php3?roa=679