Mechanisms for handling nested dependencies in neural-network language models and humans
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Recursive processing in sentence comprehension is considered a hallmark of human linguistic abilities. However, its underlying neural mechanisms remain largely unknown. We studied whether a modern artificial neural network trained with "deep learning" methods mimics a central aspect of human sentence processing, namely the storing of grammatical number and gender information in working memory and its use in long-distance agreement (e.g., capturing the correct number agreement between subject and verb when they are separated by other phrases). Although the network, a recurrent architecture with Long Short-Term Memory units, was solely trained to predict the next word in a large corpus, analysis showed the emergence of a very sparse set of specialized units that successfully handled local and long-distance syntactic agreement for grammatical number. However, the simulations also showed that this mechanism does not support full recursion and fails with some long-range embedded dependencies. We tested the model's predictions in a behavioral experiment where humans detected violations in number agreement in sentences with systematic variations in the singular/plural status of multiple nouns, with or without embedding. Human and model error patterns were remarkably similar, showing that the model echoes various effects observed in human data. However, a key difference was that, with embedded long-range dependencies, humans remained above chance level, while the model's systematic errors brought it below chance. Overall, our study shows that exploring the ways in which modern artificial neural networks process sentences leads to precise and testable hypotheses about human linguistic performance.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Mixed-effects modeling with crossed random effects for subjects and items
Baayen, R. H., Davidson, D. J., & Bates, D. M. (2008) · Journal of Memory and Language · doi:10.1016/j.jml.2007.12.005 · Cited by 8,540
The faculty of language: what is it, who has it, and how did it evolve?
Hauser, M. D., Chomsky, N., & Fitch, W. T. (2002) · Science · doi:10.1126/science.298.5598.1569 · Cited by 5,189
Meaningful Differences in the Everyday Experience of Young American Children
(1996) · Choice Reviews Online · doi:10.5860/choice.33-3435 · Cited by 4,103
Connectionism and cognitive architecture: A critical analysis
Fodor, J. A., & Pylyshyn, Z. W. (1988) · Cognition · doi:10.1016/0010-0277(88)90031-5 · Cited by 4,022
Categorical data analysis: Away from ANOVAs (transformation or not) and towards logit mixed models
Jaeger, T. F. (2008) · Journal of Memory and Language · doi:10.1016/j.jml.2007.11.007 · Cited by 3,317
Supervised Sequence Labelling with Recurrent Neural Networks
Graves, A. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-24797-2 · Cited by 3,120
Linguistic complexity: locality of syntactic dependencies
Gibson, E. (1998) · Cognition · doi:10.1016/s0010-0277(98)00034-1 · Cited by 2,537
Contributions of memory circuits to language: the declarative/procedural model
Ullman, M. T. (2004) · Cognition · doi:10.1016/j.cognition.2003.10.008 · Cited by 1,893
Cited by
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.04615 · Cited by 569
Self-citation(2021) · doi:10.18653/v1/2021.conll-1.15 · Cited by 51
Lampinen, A. (2024) · Computational Linguistics · doi:10.1162/coli_a_00525 · Cited by 32
“, 2020), and in particular recursive dependencies (Wilcox et al., 2019; Lakretz et al., 2021; Hahn et al., 2022).”
InfluentialLampinen, A. K. (2022) · arXiv · doi:10.48550/arxiv.2210.15303 · Cited by 32
(2022) · doi:10.18653/v1/2022.conll-1.8 · Cited by 5
Metadata
- Authors
- Lakretz, Y., Hupkes, D., Vergallito, A., Marelli, M., Baroni, M., & Dehaene, S.
- Venue
- Cognition
- Publisher
- Elsevier BV
- Published
- 2021-08
- Volume
- 213
- Pages
- 104699
- ISSN
- 0010-0277 (ISSN-L)
- OpenAlex
- W3159684727
- Cited by
- 60
- References
- 19
- FWCI
- 5.49
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Mechanisms for handling nested dependencies in neural-network language models and humans. https://app.cochat.ai/papers/10.1016/j.cognition.2021.104699
- The paper
- Lakretz, Y., Hupkes, D., Vergallito, A., Marelli, M., Baroni, M., & Dehaene, S. (2021). Mechanisms for handling nested dependencies in neural-network language models and humans. Cognition. https://doi.org/10.1016/j.cognition.2021.104699
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.