On the Diachronic Stability of Irregularity in Inflectional Morphology

2018/04/23 by Ryan Cotterell, Christo Kirov, Cotterell, Ryan +5 · 2 citations
Computer Science · Social Sciences · #Natural Language Processing Techniques #Language and cultural evolution #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1804.08262

Abstract

Many languages' inflectional morphological systems are replete with irregulars, i.e., words that do not seem to follow standard inflectional rules. In this work, we quantitatively investigate the conditions under which irregulars can survive in a language over the course of time. Using recurrent neural networks to simulate language learners, we test the diachronic relation between frequency of words and their irregularity.

Citations

• From usage to grammar: The mind's response to repetition

Cited by

• Learning inflection classes using Adaptive Resonance Theory
• Computational Morphology with Neural Network Approaches

Related

• Morphological Irregularity Correlates with Frequency
• Falling Through the Gaps: Neural Architectures as Models of Morphological Rule Learning
• On the Complexity and Typology of Inflectional Morphological Systems
• Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge
• Morphological Inflection: A Reality Check