Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 51 of the 52 references it cites were found in a registry or an index, and 1 are not checked yet.

Syntactic Structure from Deep Learning

Open access
Linzen, Tal, Baroni, Marco · 2021 · Annual Review of Linguistics

Abstract

Modern deep neural networks achieve impressive performance in engineering applications that require extensive linguistic skills, such as machine translation. This success has sparked interest in probing whether these models are inducing human-like grammatical knowledge from the raw data they are exposed to and, consequently, whether they can shed new light on long-standing debates concerning the innate structure necessary for language acquisition. In this article, we survey representative studies of the syntactic abilities of deep networks and discuss the broader implications that this work has for theoretical linguistics.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1146/annurev-linguistics-032020-051035

Cites

51 of 52 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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

Show all 48 references

Research works printed but not linked: 27

  1. Chaves RP., 2020, Proc. Soc. Comput. Linguist., 3, 20
  2. Chomsky N., 1965, Aspects of the Theory of Syntax
  3. Chomsky N., 1986, Knowledge of Language: Its Nature, Origin, and Use
  4. Chomsky N., 1995, The Minimalist Program
  5. Chomsky N, 1963, In Handbook of Mathematical Psychology, 2, 269
  6. Chowdhury S, 2018, Proceedings of the 27th International Conference on Computational Linguistics, 133
  7. Churchland P., 1989, A Neurocomputational Perspective: The Nature of Mind and the Structure of Science
  8. Devlin J, 2019, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 4171
  9. Elman JL, 1998, Rethinking Innateness: A Connectionist Perspective on Development
  10. Goldberg A., 2019, Explain Me This: Creativity, Competition, and the Partial Productivity of Constructions
  11. Hewitt J, 2019, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1, 4129
  12. Jurafsky D, 2008, Speech and Language Processing
  13. Lakretz Y, 2019, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 11
  14. Lasnik H, 2017, Oxford Handbook of Universal Grammar, 221
  15. Linzen T, 2018, The 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP: Proceedings of the First Workshop
  16. Linzen T, 2019, The BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP at ACL 2019: Proceedings of the Second Workshop
  17. Linzen T, 2018, Proceedings of the 40th Annual Conference of the Cognitive Science Society, 692
  18. McCoy T, 2018, Proceedings of the 40th Annual Conference of the Cognitive Science Society, 2093
  19. Mitchell TM., 1980, The need for biases in learning generalizations
  20. Radford A, 2019, Language models are unsupervised multitask learners
  21. Raffel C, Shazeer N, Roberts A, Lee K, Narang S, et al. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv:1910.10683 [cs.LG] · arXiv
  22. Ross J., 1967, Constraints on variables in syntax
  23. Socher R, 2011, ICML'11: Proceedings of the 28th International Conference on Machine Learning, 129
  24. Sutskever I, 2014, NIPS'14: Proceedings of the 27th International Conference on Neural Information Processing Systems, 2, 3104
  25. van Schijndel M, 2018, Proceedings of the 40th Annual Conference of the Cognitive Science Society, 2603
  26. Vaswani A, 2017, NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems, 6000
  27. Weston J., 2016, NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems, 829

Cited by

See all 227

Metadata

Authors
Linzen, T., & Baroni, M.
Affiliations
  • New York University (US)
  • Institució Catalana de Recerca i Estudis Avançats (ES)
Venue
Annual Review of Linguistics
Published
2021-01-14
Volume
7
Issue
1
Pages
195-212
ISSN
  • 2333-9683 (ISSN-L)
  • 2333-9691
OpenAlex
W3018827121
Cited by
202
References
48
Citations by year
2026: 17 · 2025: 31 · 2024: 33 · 2023: 39 · 2022: 37 · 2021: 36
FWCI
50.70
Type
journal article
Language
en
Open access
Locations
  • Annual Review of Linguistics (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Social Sciences › Arts and Humanities › Language and Linguistics › Syntax, Semantics, Linguistic Variation
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Social Sciences › Psychology › Developmental and Educational Psychology › Language Development and Disorders
Keywords
syntactic structure, deep neural network, grammatical knowledge, language acquisition, innate language faculty, machine translation, linguistic theory

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Syntactic Structure from Deep Learning. https://app.cochat.ai/papers/10.1146/annurev-linguistics-032020-051035
The paper
Linzen, T., & Baroni, M. (2021). Syntactic Structure from Deep Learning. Annual Review of Linguistics. https://doi.org/10.1146/annurev-linguistics-032020-051035

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.