A radically emergentist approach to phonological features: implications for grammars

Phonological features are often assumed to be innate (Chomsky & Halle 1968) or learned as a prerequisite for learning grammar (Dresher 2013). In this paper, I show an alternative approach: features are learned in parallel with grammar. This allows for addressing an interesting question: is it really optimal that the phonological grammar only use phonological features to refer to segmental material (Chomsky & Halle 1968), or could it be more advantageous for the grammar to refer to segmental material on more than one level of representation? The learner considered here finds that it is only optimal for the grammar to use phonological features to refer to multiple segments in the same pattern (e.g., the class of nasals), but when a pattern refers to a single segment, it may be at least equally good for the grammar to refer to this single segment as a bare segment label (for instance, [m] instead of [labial, nasal]). In this way, the grammar uses different kinds of representational units (features and non-features) for the same sound – which mimics models with multiple layers of representation (such as Goldrick 2001, Boersma 2007).