Generative Linguistics and Neural Networks at 60: Foundation, Friction, and Fusion
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
The birthdate of both generative linguistics and neural networks can be taken as 1957, the year of the publication of foundational work by both Noam Chomsky and Frank Rosenblatt. This article traces the development of these two approaches to cognitive science, from their largely autonomous early development in the first thirty years, through their collision in the 1980s around the past-tense debate (Rumelhart & McClelland 1986, Pinker & Prince 1988) and their integration in much subsequent work up to the present. Although this integration has produced a considerable body of results, the continued general gulf between these two lines of research is likely impeding progress in both: on learning in generative linguistics, and on the representation of language in neural modeling. The article concludes with a brief argument that generative linguistics is unlikely to fulfill its promise of accounting for language learning if it continues to maintain its distance from neural and statistical approaches to learning.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
A logical calculus of the ideas immanent in nervous activity
McCulloch, W. S., & Pitts, W. (1943) · The Bulletin of Mathematical Biophysics · doi:10.1007/bf02478259 · Cited by 18,566
The perceptron: A probabilistic model for information storage and organization in the brain.
Rosenblatt, F. (1958) · Psychological Review · doi:10.1037/h0042519 · Cited by 12,280
Skinner, B. F. (1957) · doi:10.1037/11256-000 · Cited by 5,759
The Organization of Behavior; A Neuropsychological Theory.
Attneave, F., B., M., & Hebb, D. O. (1950) · The American Journal of Psychology · doi:10.2307/1418888 · Cited by 5,146
A large annotated corpus for learning natural language inference
Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1075 · Cited by 3,377 · cited 1×
“…that incorporate compositional and hierarchical linguistic structures into neural networks with the aim of improving their performance on AI tasks (e.g. Andreas & Ghahramani 2013, Socher et al. 2013, Bowman, Angeli, et al. 2015, Yogatama et al. 2016; though see also Bowman, Manning, & Potts 2015).”
On the proper treatment of connectionism
Smolensky, P. (1988) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00052432 · Cited by 2,441
PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS
ROSENBLATT, F. (1961) · doi:10.21236/ad0256582 · Cited by 1,691
Adversarial Examples for Evaluating Reading Comprehension Systems
Jia, R., & Liang, P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1215 · Cited by 1,410 · cited 1×
“Alongside these proposals are observations about the fragility of models that es-chew linguistic structure when they are tested on linguistically challenging data (e.g. Ettinger et al. 2017, Jia & Liang 2017).”
Distributed representations, simple recurrent networks, and grammatical structure
Elman, J. L. (1991) · Machine Learning · doi:10.1007/bf00114844 · Cited by 1,354
Neural Network Methods for Natural Language Processing
Goldberg, Y. (2017) · Synthesis Lectures on Human Language Technologies · doi:10.1007/978-3-031-02165-7 · Cited by 821
Recurrent Neural Network Grammars
Dyer, C., Kuncoro, A., Ballesteros, M., & Smith, N. A. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1024 · Cited by 517 · cited 2×
“In proposing recurrent neural network grammars , Dyer, Kuncoro, Ballesteros, and Smith (2016) hypothesize that RNNs do in fact need to be supplemented with hierarchical structure.”
Context-sensitive coding, associative memory, and serial order in (speech) behavior.
Wickelgran, W. A. (1969) · Psychological Review · doi:10.1037/h0026823 · Cited by 376 · cited 1×
“To represent phonological contexts, a single node encodes features of both the preceding and following phone, as well as the central phone—a triphone representation called a ‘Wickelfeature’ (after Wickelgran 1969).”
Cited by
Deep problems with neural network models of human vision
Bowers, J. S., Malhotra, G., Dujmović, M., Llera Montero, M., Tsvetkov, C., Biscione, V., Puebla, G., Adolfi, F., Hummel, J. E., Heaton, R. F., et al. (2023) · Behavioral and Brain Sciences · doi:10.1017/s0140525x22002813 · Cited by 204
Chen, H., & Luo, X. (2019) · Advanced Engineering Informatics · doi:10.1016/j.aei.2019.100959 · Cited by 133
Bigger is not always better: The importance of human-scale language modeling for psycholinguistics
Wilcox, E. G., Hu, M. Y., Mueller, A., Warstadt, A., Choshen, L., Zhuang, C., Williams, A., Cotterell, R., & Linzen, T. (2025) · Journal of Memory and Language · doi:10.1016/j.jml.2025.104650 · Cited by 9
Metadata
- Authors
- Pater, J.
- Venue
- Language
- Publisher
- Cambridge University Press (CUP)
- Published
- 2019-03
- Volume
- 95
- Issue
- 1
- Pages
- e41-e74
- ISSN
- 0097-8507 (ISSN-L)
- 1535-0665
- OpenAlex
- W2905623858
- Cited by
- 88
- References
- 13
- FWCI
- 63.74
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.