From experiment results to a constraint hierarchy with the 'Rank Centrality' algorithm

Abstract

Rank Centrality (RC; Negahban, Oh, & Shah 2017) is a rank-aggregation algorithm that computes a total ranking of elements from noisy pairwise ranking information. I test RC as an alternative to incremental error-driven learning algorithms such as GLA-MaxEnt (Boersma & Hayes 2001; Jäger 2007) for modeling a constraint hierarchy on the basis of two-alternative forced-choice experiment results. For the case study examined here, RC agrees well with GLA-MaxEnt on the ordering of the constraints, but differs somewhat on the distance between constraints; in particular, RC assigns more extreme (low) positions to constraints at the bottom of the hierarchy than GLA-MaxEnt does. Overall, these initial results are promising, and RC merits further investigation as a constraint-ranking method in experimental linguistics.