Parsing Minimalist Languages with Interpreted Regular Tree Grammars

Minimalist Grammars (MGs) (Stabler, 1997) are a formalisation of Chomsky’s minimalist program (Chomsky, 1995), which currently dominates much of mainstream syntax. MGs are simple and intuitive to work with, and are mildly context sensitive (Michaelis, 1998), putting them in the right general class for human language (Joshi, 1985).1 Minimalist Grammars are known to be more succinct than their Multiple ContextFree equivalents (Stabler, 2013), to have regular derivation tree languages (Kobele et al., 2007), and to be recognisable in polynomial time (Harkema, 2001) with a bottom-up CKY-like parser. However, the polynomial is large, O(n4k+4) where k is a grammar constant. By approaching minimalist grammars from the perspective of Interpreted Regular Tree Grammars, we show that standard chart-based parsing is substantially computationally cheaper than previously thought at O(n2k+3 · 2k).