Investigating Cross-Linguistic Adjective Ordering Tendencies with a Latent-Variable Model

TL;DR

This paper introduces a corpus-driven latent-variable model that accurately predicts adjective orderings across 24 languages, providing evidence for universal hierarchical tendencies in adjective sequencing.

Contribution

It presents the first purely corpus-based model for multilingual adjective ordering, demonstrating cross-linguistic universal tendencies with high accuracy.

Findings

Model accurately orders adjectives in 24 languages

Provides evidence for universal hierarchical adjective ordering

Works across different training and testing languages

Abstract

Across languages, multiple consecutive adjectives modifying a noun (e.g. "the big red dog") follow certain unmarked ordering rules. While explanatory accounts have been put forward, much of the work done in this area has relied primarily on the intuitive judgment of native speakers, rather than on corpus data. We present the first purely corpus-driven model of multi-lingual adjective ordering in the form of a latent-variable model that can accurately order adjectives across 24 different languages, even when the training and testing languages are different. We utilize this novel statistical model to provide strong converging evidence for the existence of universal, cross-linguistic, hierarchical adjective ordering tendencies.