Capturing gradience in long-distance phonology using probabilistic tier-based strictly local grammars

Abstract

Phonological processes often exhibit gradience, both in response frequencies and in acceptability judgments. This paper presents a variation of tier-based strictly local grammars, probabilistic tier-based strictly local grammars (pTSL), which assign probabilities to input strings and are well-suited to modeling such variability, particularly for long-distance processes. pTSL naturally extends categorical tier-based strictly local grammars by probabilizing the projection function. After describing the formal properties of pTSL, I illustrate its application using data from Hungarian and Uyghur. pTSL is able to capture distancebased decay in these languages without an explicit notion of distance, and provides a unified account of gradient blocking and distancebased decay. I finish by outlining some of the limitations of pTSL, and how further extensions may overcome these.