# Inflecting when there's no majority: Limitations of encoder-decoder neural networks as cognitive models for German plurals

arXiv: https://arxiv.org/abs/2005.08826 · HTML: https://mlsanity.com/paper/2005.08826/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2020.

## Built on by (most cited first, 13 of 13)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Why Linguistics Will Thrive in the 21st Century: A Reply to Piantadosi (2023)](https://mlsanity.com/paper/2308.03228/) (2023)
- [Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model](https://mlsanity.com/paper/2310.15113/) (2023)
- [Modeling morphology with Linear Discriminative Learning: considerations and design choices](https://mlsanity.com/paper/2106.07936/) (2021)
- [Is deeper always better? Replacing linear mappings with deep learning networks in the Discriminative Lexicon Model](https://mlsanity.com/paper/2410.04259/) (2024)
- [The Greedy and Recursive Search for Morphological Productivity](https://mlsanity.com/paper/2105.05790/) (2021)
- [A Comprehensive Comparison of Neural Networks as Cognitive Models of Inflection](https://mlsanity.com/paper/2210.12321/) (2022)
- [Character-aware Transformers Learn an Irregular Morphological Pattern Yet None Generalize Like Humans](https://mlsanity.com/paper/2602.14100/) (2026)
- [Falling Through the Gaps: Neural Architectures as Models of Morphological Rule Learning](https://mlsanity.com/paper/2105.03710/) (2021)
- [How do we get there? Evaluating transformer neural networks as cognitive models for English past tense inflection](https://mlsanity.com/paper/2210.09167/) (2022)
- [Evaluating Transformer Models and Human Behaviors on Chinese Character Naming](https://mlsanity.com/paper/2303.12294/) (2023)
- [Transformers over-extend what humans underlearn: the case of Spanish L-shaped morphome](https://mlsanity.com/paper/2507.21556/) (2025)
- [Analysis of the Neglect-Zero Effect in Large Language Models](https://mlsanity.com/paper/2606.05864/) (2026)

## Abstract (arXiv)

Can artificial neural networks learn to represent inflectional morphology and generalize to new words as human speakers do? Kirov and Cotterell (2018) argue that the answer is yes: modern Encoder-Decoder (ED) architectures learn human-like behavior when inflecting English verbs, such as extending the regular past tense form -(e)d to novel words. However, their work does not address the criticism raised by Marcus et al. (1995): that neural models may learn to extend not the regular, but the most frequent class -- and thus fail on tasks like German number inflection, where infrequent suffixes like -s can still be productively generalized. To investigate this question, we first collect a new dataset from German speakers (production and ratings of plural forms for novel nouns) that is designed to avoid sources of information unavailable to the ED model. The speaker data show high variability, and two suffixes evince 'regular' behavior, appearing more often with phonologically atypical inputs. Encoder-decoder models do generalize the most frequently produced plural class, but do not show human-like variability or 'regular' extension of these other plural markers. We conclude that modern neural models may still struggle with minority-class generalization.