# Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate

arXiv: https://arxiv.org/abs/1807.04783 · HTML: https://mlsanity.com/paper/1807.04783/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2018.

## Built on by (most cited first, 27 of 27)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Word Acquisition in Neural Language Models](https://mlsanity.com/paper/2110.02406/) (2021)
- [The Grammar-Learning Trajectories of Neural Language Models](https://mlsanity.com/paper/2109.06096/) (2021)
- [Anything Goes? A Crosslinguistic Study of (Im)possible Language Learning in LMs](https://mlsanity.com/paper/2502.18795/) (2025)
- [Evaluating Neural Language Models as Cognitive Models of Language Acquisition](https://mlsanity.com/paper/2310.20093/) (2023)
- [From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes](https://mlsanity.com/paper/2410.22906/) (2024)
- [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)
- [Second Language Acquisition of Neural Language Models](https://mlsanity.com/paper/2306.02920/) (2023)
- [Modeling morphology with Linear Discriminative Learning: considerations and design choices](https://mlsanity.com/paper/2106.07936/) (2021)
- [From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks](https://mlsanity.com/paper/2405.15164/) (2024)
- [IPA-CHILDES & G2P+: Feature-Rich Resources for Cross-Lingual Phonology and Phonemic Language Modeling](https://mlsanity.com/paper/2504.03036/) (2025)
- [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)
- [Computational Morphology with Neural Network Approaches](https://mlsanity.com/paper/2105.09404/) (2021)
- [Not quite there yet: Combining analogical patterns and encoder-decoder networks for cognitively plausible inflection](https://mlsanity.com/paper/2108.03968/) (2021)
- [A Comprehensive Comparison of Neural Networks as Cognitive Models of Inflection](https://mlsanity.com/paper/2210.12321/) (2022)
- [BabyLM's First Words: Word Segmentation as a Phonological Probing Task](https://mlsanity.com/paper/2504.03338/) (2025)
- [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)
- [Does Vision Accelerate Hierarchical Generalization in Neural Language Learners?](https://mlsanity.com/paper/2302.00667/) (2023)
- [Robustness of the Random Language Model](https://mlsanity.com/paper/2309.14913/) (2023)
- [Exploring Linguistic Probes for Morphological Generalization](https://mlsanity.com/paper/2310.13686/) (2023)
- [LLMs' morphological analyses of complex FST-generated Finnish words](https://mlsanity.com/paper/2407.08269/) (2024)
- [How do we get there? Evaluating transformer neural networks as cognitive models for English past tense inflection](https://mlsanity.com/paper/2210.09167/) (2022)
- [Transformers over-extend what humans underlearn: the case of Spanish L-shaped morphome](https://mlsanity.com/paper/2507.21556/) (2025)
- [Probing Character-level Transformers for the Spanish L-shaped Morphome](https://mlsanity.com/paper/2608.03452/) (2026)
- [The Dynamics of Quasiregular Neural Learning](https://mlsanity.com/paper/2609.26018/) (2026)

## Abstract (arXiv)

Can advances in NLP help advance cognitive modeling? We examine the role of artificial neural networks, the current state of the art in many common NLP tasks, by returning to a classic case study. In 1986, Rumelhart and McClelland famously introduced a neural architecture that learned to transduce English verb stems to their past tense forms. Shortly thereafter, Pinker & Prince (1988) presented a comprehensive rebuttal of many of Rumelhart and McClelland's claims. Much of the force of their attack centered on the empirical inadequacy of the Rumelhart and McClelland (1986) model. Today, however, that model is severely outmoded. We show that the Encoder-Decoder network architectures used in modern NLP systems obviate most of Pinker and Prince's criticisms without requiring any simplication of the past tense mapping problem. We suggest that the empirical performance of modern networks warrants a re-examination of their utility in linguistic and cognitive modeling.