Hostname: page-component-6766d58669-bp2c4 Total loading time: 0 Render date: 2026-05-21T01:52:51.054Z Has data issue: false hasContentIssue false

Typology Meets Statistical Modeling: The German Gender System

Published online by Cambridge University Press:  01 January 2026

Sebastian Fedden*
Affiliation:
Université Sorbonne Nouvelle/LACITO, Ludwig-Maximilians-Universität München, and University of Surrey
Matías Guzmán Naranjo*
Affiliation:
Universität Freiburg
Greville G. Corbett*
Affiliation:
University of Surrey and Max Planck Institute for Evolutionary Anthropology, Leipzig

Abstract

The German gender system is known for its complexity, and there is a persistent misconception that it is largely arbitrary, and hence a challenge for the typology of gender systems. In response, we construct a database of more than 30,000 German nouns and show that a boosting tree model achieves a predictive success of 96%. Even more surprising, the model performs at 87% when trained on just the 100 most frequent nouns. We thus demonstrate that the complex German system fits into a typologically well-known scheme, being a combination of semantic and formal assignment principles. In addition to our success with the specific problem, we show the value of statistical modeling for typologists and reflect on what exactly we can learn from these techniques.

Information

Type
Research Article
Copyright
Copyright © Linguistic Society of America 2025

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

Supplementary material: File

Fedden et al. supplementary material

Fedden et al. supplementary material
Download Fedden et al. supplementary material(File)
File 322.8 KB