Parsing syllables: modeling OT computationally
Michael Hammond
University of Arizona
	Optimality Theory (Prince & Smolensky, 1993; McCarthy & Prince, 1993) maintains that phonological generalizations can be treated by a two-step process.  First, all possible pronunciations for some string are generated by the GEN operation. Then, the best of these different pronunciations is chosen by a set of ranked and violable constraints. This is the dominant theory of phonology today. 	This theory poses a serious problem for theories of phonological performance; the model cannot be implemented in real time because the candidate set is infinite. Even if we eliminate a number of options in generating candidates, we are still left with an extremely large number of candidate pronunciations to sift through in finite time.
	In this paper, I propose to implement syllabification in OT as a parser. I propose several innovations that result in a finite and small candidate set. The candidate set problem is handled with several moves: i) MAX and DEP violations are not hypothesized by the parser, ii) candidates are encoded locally, and iii) EVAL is applied constraint by constraint.
	The parser I propose is implemented in Prolog. It has a number of desirable consequences. First, it runs and thus provides an existence proof that syllabification can be implemented in OT.  There are a number of other desirable consequences as well. First, constraints are implemented as finite-state transducers. Second, the parser makes several interesting claims about the phonological properties of so-called nonrecoverable insertions and deletions. Third, the implementation suggests some particular reformulations of some of the benchmark constraints in the OT arsenal, e.g.  *COMPLEX, PARSE, ONSET, and NOCODA.
	Finally, the implementation is compared with various other proposals in the literature, e.g. Ellison (1994), Hammond (1995), Tesar (1995), and Eisner (1997).