Modelling Verbal Morphology in Nen

TL;DR

This paper models the complex verbal morphology of Nen using machine learning, analyzing error types, data sensitivity, and morphological patterns like syncretism in a low-resource setting.

Contribution

It applies state-of-the-art morphological reinflection models to Nen, a low-resource language with complex morphology, and categorizes error types and data effects.

Findings

Model sensitivity to training data distribution

Error patterns linked to morphological complexity

Inference of morphological patterns like syncretism

Abstract

Nen verbal morphology is remarkably complex; a transitive verb can take up to 1,740 unique forms. The combined effect of having a large combinatoric space and a low-resource setting amplifies the need for NLP tools. Nen morphology utilises distributed exponence - a non-trivial means of mapping form to meaning. In this paper, we attempt to model Nen verbal morphology using state-of-the-art machine learning models for morphological reinflection. We explore and categorise the types of errors these systems generate. Our results show sensitivity to training data composition; different distributions of verb type yield different accuracies (patterning with E-complexity). We also demonstrate the types of patterns that can be inferred from the training data through the case study of syncretism.