Learning Tier-based Strictly 2-Local Languages

Abstract

The Tier-based Strictly 2-Local (TSL 2 ) languages are a class of formal languages which have been shown to model long-distance phonotactic generalizations in natural language (Heinz et al., 2011). This paper introduces the Tier-based Strictly 2-Local Inference Algorithm (2TSLIA), the first nonenumerative learner for the TSL 2 languages. We prove the 2TSLIA is guaranteed to converge in polynomial time on a data sample whose size is bounded by a constant.