Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network
Verna Dankers, Anna Langedijk, Kate McCurdy, Adina Williams, Dieuwke Hupkes
Abstract
Inflectional morphology has since long been a useful testing ground for broader questions about generalisation in language and the viability of neural network models as cognitive models of language. Here, in line with that tradition, we explore how recurrent neural networks acquire the complex German plural system and reflect upon how their strategy compares to human generalisation and rule-based models of this system. We perform analyses including behavioural experiments, diagnostic classification, representation analysis and causal interventions, suggesting that the models rely on features that are also key predictors in rule-based models of German plurals. However, the models also display shortcut learning, which is crucial to overcome in search of more cognitively plausible generalisation behaviour.- Anthology ID:
- 2021.conll-1.8
- Volume:
- Proceedings of the 25th Conference on Computational Natural Language Learning
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Arianna Bisazza, Omri Abend
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 94–108
- Language:
- URL:
- https://aclanthology.org/2021.conll-1.8
- DOI:
- 10.18653/v1/2021.conll-1.8
- Cite (ACL):
- Verna Dankers, Anna Langedijk, Kate McCurdy, Adina Williams, and Dieuwke Hupkes. 2021. Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network. In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 94–108, Online. Association for Computational Linguistics.
- Cite (Informal):
- Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network (Dankers et al., CoNLL 2021)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2021.conll-1.8.pdf
- Code
- i-machine-think/morphology_and_generalisation