The first formalizations of a modern WP model were proposed, more or less simultaneously, in Chomsky (1965) and Matthews (1965). Both accounts proceeded from the observation that the inflectional features that were distinctive for a given word or inflection class could be specified independently of their formal realization. In brief and programmatic remarks about the German declensional system, Chomsky (1965) notes that “the traditional paradigmatic treatment” could be reconstructed by a model that ‘interprets’ features:
In short, the theory of syntactic features developed earlier can incorporate the traditional paradigmatic treatment directly. The system of paradigms is simply described as a system of features, one (or perhaps some hierarchical configuration) corresponding to each of the dimensions that define the system of paradigms. Interpretive phonological rules, some quite specific, some of considerable generality, then operate on the phonological matrix of the lexical entry, giving, finally, a phonetic matrix. (Chomsky 1965:172)
A similar approach is outlined in greater detail in Matthews (1965) in his analysis of the inflectional component of a WP model:
The present paper is intended to supply a part of this formulation. It is restricted to inflectional problems alone: to be more precise, it deals with that subsection of the grammar (we will call it the inflectional component) which assigns a realization, or various alternative realizations, to each grammatical word. (Matthews 1965:142)
The central insight expressed in these passages is that a flexible relation between features and forms can be defined by purely interpretive rules that ‘spell-out’ or ‘realize’ features associated with a paradigm cell or feature bundle.