CoChat

Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations

Open access
Sinclair, Arabella, Jumelet, Jaap, Zuidema, Willem, Fernández, Raquel · 2022 · Transactions of the Association for Computational Linguistics
Cited by 48

The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.

Abstract

We investigate the extent to which modern neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how priming can be used to study the potential of these models to learn abstract structural information, which is a prerequisite for good performance on tasks that require natural language understanding skills. We introduce a novel metric and release Prime-LM, a large corpus where we control for various linguistic factors that interact with priming strength. We find that Transformer models indeed show evidence of structural priming, but also that the generalizations they learned are to some extent modulated by semantic information. Our experiments also show that the representations acquired by the models may not only encode abstract sequential structure but involve certain level of hierarchical syntactic information. More generally, our study shows that the priming paradigm is a useful, additional tool for gaining insights into the capacities of language models and opens the door to future priming-based investigations that probe the model’s internal states.1

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.

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

Integrity signals

Registry

Crossref · 10.1162/tacl_a_00504

Cites

18 of 18 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.

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.

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

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 18 references

Research works printed but not linked: 73

  1. Alishahi, 2019, Analyzing and interpreting neural networks for NLP: A report on the first BlackboxNLP Workshop, Natural Language Engineering, 25, 543, 10.1017/S135132491900024X · DOI
  2. Baroni, 2022, On the proper role of linguistically-oriented deep net analysis in linguistic theorizing
  3. Bernolet, 2010, Does verb bias modulate syntactic priming?, Cognition, 114, 455, 10.1016/j.cognition.2009.11.005 · DOI · Paper page
  4. Black, 2021, GPT-Neo: Large scale autoregressive language modeling with mesh-tensorflow, 10.18653/v1/2022.bigscience-1.9 · DOI · Paper page
  5. Bock, 1989, Closed-class immanence in sentence production, Cognition, 31, 163, 10.1016/0010-0277(89)90022-X · DOI · Paper page
  6. Bock, 2007, Persistent structural priming from language comprehension to language production, Cognition, 104, 437, 10.1016/j.cognition.2006.07.003 · DOI · Paper page
  7. Boleda, 2020, Distributional semantics and linguistic theory, Annual Review of Linguistics, 6, 213, 10.1146/annurev-linguistics-011619-030303 · DOI · Paper page
  8. Branigan, 1999, Syntactic priming in written production: Evidence for rapid decay, Psychonomic Bulletin & Review, 6, 635, 10.3758/BF03212972 · DOI · Paper page
  9. Branigan, 2006, The role of local and global syntactic structure in language production: Evidence from syntactic priming, Language and Cognitive Processes, 21, 974, 10.1080/016909600824609 · DOI · Paper page
  10. Bresnan, 2007, Predicting the dative alternation, 69
  11. Chang, 2000, Structural priming as implicit learning: A comparison of models of sentence production, Journal of Psycholinguistic Research, 29, 217, 10.1023/A:1005101313330 · DOI · Paper page
  12. Cleland, 2003, The use of lexical and syntactic information in language production: Evidence from the priming of noun-phrase structure, Journal of Memory and Language, 49, 214, 10.1016/S0749-596X(03)00060-3 · DOI · Paper page
  13. Cochran, 1977, Sampling Techniques
  14. Davies, 2009, The 385+ million word Corpus of Contemporary American English (1990–2008+): Design, architecture, and linguistic insights, International Journal of Corpus Linguistics, 14, 159, 10.1075/ijcl.14.2.02dav · DOI · Paper page
  15. Davis, 2020, Discourse structure interacts with reference but not syntax in neural language models, 396, 10.18653/v1/2020.conll-1.32 · DOI
  16. Dubey, 2008, A probabilistic corpus-based model of syntactic parallelism, Cognition, 109, 326, 10.1016/j.cognition.2008.09.006 · DOI
  17. Fares, 2017, Word vectors, reuse, and replicability: Towards a community repository of large-text resources, 271
  18. Fine, 2013, Evidence for implicit learning in syntactic comprehension, Cognitive Science, 37, 578, 10.1111/cogs.12022 · DOI · Paper page
  19. Foster, 2007, Avoiding repetition in generated text, 33, 10.3115/1610163.1610170 · DOI
  20. Zihao, 2021, A theoretical analysis of the repetition problem in text generation, 12848
  21. Futrell, 2019, Neural language models as psycholinguistic subjects: Representations of syntactic state, 32, 10.18653/v1/N19-1004 · DOI · Paper page
  22. Goldwater, 2011, Structural priming as structure-mapping: Children use analogies from previous utterances to guide sentence production, Cognitive Science, 35, 156, 10.1111/j.1551-6709.2010.01150.x · DOI
  23. Gries, 2005, Syntactic priming: A corpus-based approach, Journal of Psycholinguistic Research, 34, 365, 10.1007/s10936-005-6139-3 · DOI · Paper page
  24. Gulordava, 2018, Colorless green recurrent networks dream hierarchically, 1195, 10.18653/v1/n18-1108 · DOI · Paper page
  25. Hessel, 2021, How effective is BERT without word ordering? Implications for language understanding and data privacy, 204, 10.18653/v1/2021.acl-short.27 · DOI
  26. Jennifer, 2020, A systematic assessment of syntactic generalization in neural language models, pages 1725–pages 1744
  27. Hupkes, 2018, Visualisation and ‘diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure, Journal of Artificial Intelligence Research, 61, 907, 10.1613/jair.1.11196 · DOI · Paper page
  28. Ivanova, 2017, Do you what I say? People reconstruct the syntax of anomalous utterances, Language, Cognition and Neuroscience, 32, 175, 10.1080/23273798.2016.1236976 · DOI
  29. Ivanova, 2012, The comprehension of anomalous sentences: Evidence from structural priming, Cognition, 122, 193, 10.1016/j.cognition.2011.10.013 · DOI
  30. Florian Jaeger, 2013, Alignment as a consequence of expectation adaptation: Syntactic priming is affected by the prime’s prediction error given both prior and recent experience, Cognition, 127, 57, 10.1016/j.cognition.2012.10.013 · DOI · Paper page
  31. Jeffreys, 1961, Theory of Probability
  32. Józefowicz, 2016, Exploring the limits of language modeling, CoRR
  33. Jumelet, 2020, diagNNose: A library for neural activation analysis, pages 342–pages 350, 10.18653/v1/2020.blackboxnlp-1.32 · DOI
  34. Jumelet, 2021, Language models use monotonicity to assess NPI licensing, 4958, 10.18653/v1/2021.findings-acl.439 · DOI
  35. Kaschak, 2011, Structural priming as implicit learning: Cumulative priming effects and individual differences, Psychonomic Bulletin & Review, 18, 1133, 10.3758/s13423-011-0157-y · DOI
  36. Kass, 1995, Bayes factors, Journal of the American Statistical Association, 90, 773, 10.1080/01621459.1995.10476572 · DOI · Paper page
  37. Kassner, 2020, Negated and misprimed probes for pretrained language models: Birds can talk, but cannot fly, 7811, 10.18653/v1/2020.acl-main.698 · DOI · Paper page
  38. Kodner, 2020, Overestimation of syntactic representation in neural language models, pages 1757–pages 1762, 10.18653/v1/2020.acl-main.160 · DOI
  39. Lakretz, 2021, Mechanisms for handling nested dependencies in neural-network language models and humans, Cognition, 213, 10.1016/j.cognition.2021.104699 · DOI · Paper page
  40. Lan, 2020, ALBERT: A lite BERT for self-supervised learning of language representations
  41. Li, 2022, Neural reality of argument structure constructions, 7410, 10.18653/v1/2022.acl-long.512 · DOI
  42. Linzen, 2016, Assessing the ability of LSTMs to learn syntax-sensitive dependencies, Transactions of the Association for Computational Linguistics, 4, 521, 10.1162/tacl_a_00115 · DOI · Paper page
  43. Liu, 2019, RoBERTa: A robustly optimized BERT pretraining approach, CoRR
  44. Lovering, 2021, Predicting inductive biases of pre-trained models
  45. Madabushi, 2020, CxGBERT: BERT meets construction grammar, 4020, 10.18653/v1/2020.coling-main.355 · DOI
  46. Mahowald, 2016, A meta-analysis of syntactic priming in language production, Journal of Memory and Language, 91, 5, 10.1016/j.jml.2016.03.009 · DOI · Paper page
  47. Marvin, 2018, Targeted syntactic evaluation of language models, 1192, 10.1016/j.jml.2016.03.009 · DOI · Paper page
  48. Merriam-Webster, 1989, Webster’s Dictionary of English Usage
  49. Nelson, 2004, The University of South Florida free association, rhyme, and word fragment norms, Behavior Research Methods, Instruments, & Computers, 36, 402, 10.3758/BF03195588 · DOI · Paper page
  50. Newman, 2021, Refining targeted syntactic evaluation of language models, 3710, 10.18653/v1/2021.naacl-main.290 · DOI
  51. Pham, 2021, Out of order: How important is the sequential order of words in a sentence in natural language understanding tasks?, 1145, 10.18653/v1/2021.findings-acl.98 · DOI · Paper page
  52. Pickering, 1998, The representation of verbs: Evidence from syntactic priming in language production, Journal of Memory and Language, 39, 633, 10.1006/jmla.1998.2592 · DOI · Paper page
  53. Pickering, 2013, Persistent structural priming and frequency effects during comprehension., Journal of Experimental Psychology: Learning, Memory, and Cognition, 39, 890, 10.1037/a0029181 · DOI
  54. Prasad, 2019, Using priming to uncover the organization of syntactic representations in neural language models, 66, 10.18653/v1/K19-1007 · DOI · Paper page
  55. Radford, 2019, Language models are unsupervised multitask learners, OpenAI blog, 1, 9
  56. Reitter, 2007, Against sequence priming: Evidence from constituents and distituents in corpus data
  57. Reitter, 2011, A computational cognitive model of syntactic priming, Cognitive Science, 35, 587, 10.1111/j.1551-6709.2010.01165.x · DOI · Paper page
  58. Reitter, 2014, Alignment and task success in spoken dialogue, Journal of Memory and Language, 76, 29, 10.1016/j.jml.2014.05.008 · DOI · Paper page
  59. Salazar, 2020, Masked language model scoring, 2699, 10.18653/v1/2020.acl-main.240 · DOI · Paper page
  60. Scheepers, 2003, Syntactic priming of relative clause attachments: Persistence of structural configuration in sentence production, Cognition, 89, 179, 10.1016/S0010-0277(03)00119-7 · DOI · Paper page
  61. Schrimpf, 2020, Artificial neural networks accurately predict language processing in the brain, bioRxiv
  62. Sinha, 2021, Masked language modeling and the distributional hypothesis: Order word matters pre-training for little, 2888, 10.18653/v1/2021.emnlp-main.230 · DOI · Paper page
  63. Sinha, 2021, UnNatural Language Inference, 7329, 10.18653/v1/2021.acl-long.569 · DOI · Paper page
  64. Tenney, 2019, What do you learn from context? Probing for sentence structure in contextualized word representations
  65. Tooley, 2014, On the parity of structural persistence in language production and comprehension, Cognition, 132, 101, 10.1016/j.cognition.2014.04.002 · DOI · Paper page
  66. Fox Tree, 1999, Building syntactic structure in speaking, Journal of Psycholinguistic Research, 28, 71, 10.1023/A:1023239604158 · DOI · Paper page
  67. Vamvas, 2021, On the limits of minimal pairs in contrastive evaluation, 58, 10.18653/v1/2021.blackboxnlp-1.5 · DOI
  68. van Schijndel, 2018, A neural model of adaptation in reading, pages 4704–pages 4710, 10.18653/v1/D18-1499 · DOI · Paper page
  69. Vaswani, 2017, Attention is all you need, 5998
  70. Warstadt, 2019, Investigating BERT’s knowledge of language: Five analysis methods with NPIs, 2870, 10.18653/v1/D19-1286 · DOI · Paper page
  71. Warstadt, 2020, BLiMP: A benchmark of linguistic minimal pairs for English, 351, 10.1162/tacl_a_00321 · DOI · Paper page
  72. Wheeldon, 2003, Phrase structure priming: A short-lived effect, Language and Cognitive Processes, 18, 431, 10.1080/01690960244000063 · DOI · Paper page
  73. White, 2021, A non-linear structural probe, 132

Cited by

See all 48

Metadata

Authors
Sinclair, A., Jumelet, J., Zuidema, W., & Fernández, R.
Venue
Transactions of the Association for Computational Linguistics
Publisher
MIT Press
Published
2022
Volume
10
Pages
1031-1050
ISSN
2307-387X (ISSN-L)
OpenAlex
W4296564631
Cited by
48
References
18
FWCI
3.47
Type
journal article
Language
en
Open access
diamond

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: Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations. https://app.cochat.ai/papers/10.1162/tacl_a_00504
The paper
Sinclair, A., Jumelet, J., Zuidema, W., & Fernández, R. (2022). Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00504

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.