Language processing in brains and deep neural networks: computational convergence and its limits
Open accessThe DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
A bstract: Deep Learning has recently led to major advances in natural language processing. Do these models process sentences similarly to humans, and is this similarity driven by specific principles? Using a variety of artificial neural networks, trained on image classification, word embedding, or language modeling, we evaluate whether their architectural and functional properties lead them to generate activations linearly comparable to those of 102 human brains measured with functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG). We show that image, word and contextualized word embeddings separate the hierarchical levels of language processing in the brain. Critically, we compare 3,600 embeddings in their ability to linearly map onto these brain responses. The results show that (1) the position of the layer in the network and (2) the ability of the network to accurately predict words from context are the main factors responsible for the emergence of brain-like representations in artificial neural networks. Together, these results show how perceptual, lexical and compositional representations precisely unfold within each cortical region and contribute to uncovering the governing principles of language processing in brains and algorithms.
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
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645
The free-energy principle: a unified brain theory?
Friston, K. (2010) · Nature Reviews Neuroscience · doi:10.1038/nrn2787 · Cited by 8,120 · cited 2×
“, 2017) is in many ways not biologically 195 plausible: while the brain has been repeatedly associated with a predictive coding architecture, where prediction errors 196 are computed at each level of an interconnected hierarchy of recurrent networks (Friston, 2010), transformers access an 197 unreasonably large buffer…”
BackgroundMoses: open source toolkit for statistical machine translation
Koehn, P., Zens, R., Dyer, C., Bojar, O., Constantin, A., Herbst, E., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., et al. (2007) · Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions - ACL '07 · doi:10.3115/1557769.1557821 · Cited by 4,735
A component based noise correction method (CompCor) for BOLD and perfusion based fMRI
Behzadi, Y., Restom, K., Liau, J., & Liu, T. T. (2007) · NeuroImage · doi:10.1016/j.neuroimage.2007.04.042 · Cited by 4,502
fMRIPrep: A robust preprocessing pipeline for functional MRI
Esteban, O., Markiewicz, C. J., Blair, R. W., Moodie, C. A., Isik, A. I., Erramuzpe, A., Kent, J. D., Goncalves, M., DuPre, E., Snyder, M., et al. (2019) · Nature Methods · doi:10.1038/s41592-018-0235-4 · Cited by 3,905
Automatic parcellation of human cortical gyri and sulci using standard anatomical nomenclature
Destrieux, C., Fischl, B., Dale, A., & Halgren, E. (2010) · NeuroImage · doi:10.1016/j.neuroimage.2010.06.010 · Cited by 2,956
Performance-optimized hierarchical models predict neural responses in higher visual cortex
Yamins, D. L. K., Hong, H., Cadieu, C. F., Solomon, E. A., Seibert, D., & DiCarlo, J. J. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1403112111 · Cited by 1,924
Using goal-driven deep learning models to understand sensory cortex
Yamins, D. L. K., & DiCarlo, J. J. (2016) · Nature Neuroscience · doi:10.1038/nn.4244 · Cited by 1,621
Cross-lingual Language Model Pretraining
Lample, G., & Conneau, A. (2019) · arXiv · doi:10.48550/arxiv.1901.07291 · Cited by 1,586
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Frankle, J., & Carbin, M. (2018) · arXiv · doi:10.48550/arxiv.1803.03635 · Cited by 1,529
Natural speech reveals the semantic maps that tile human cerebral cortex
Huth, A. G., de Heer, W. A., Griffiths, T. L., Theunissen, F. E., & Gallant, J. L. (2016) · Nature · doi:10.1038/nature17637 · Cited by 1,504
Human Brain Language Areas Identified by Functional Magnetic Resonance Imaging
Binder, J. R., Frost, J. A., Hammeke, T. A., Cox, R. W., Rao, S. M., & Prieto, T. (1997) · The Journal of Neuroscience · doi:10.1523/jneurosci.17-01-00353.1997 · Cited by 1,424
On Broca, brain, and binding: A new framework
Hagoort, P. (2005) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2005.07.004 · Cited by 1,411 · cited 1×
“This hierarchical pathway and a parallel motor 35 route - responsible for articulatory codes (Hickok and Poeppel, 2007) together connect with the inferior frontal gyrus, 36 repeatedly associated with the compositional processes of language (Dehaene and Cohen, 2011; Hickok and Poeppel, 37 2007; Hagoort, 2005; Mollica e…”
BackgroundThe anatomy of language: a review of 100 fMRI studies published in 2009
Price, C. J. (2010) · Annals of the New York Academy of Sciences · doi:10.1111/j.1749-6632.2010.05444.x · Cited by 1,387
(2019) · doi:10.18653/v1/p19-1356 · Cited by 1,291
Deep supervised, but not unsupervised, models may explain IT cortical representation
Khaligh-Razavi, S.-M., & Kriegeskorte, N. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003915 · Cited by 1,204
Predicting Human Brain Activity Associated with the Meanings of Nouns
Mitchell, T. M., Shinkareva, S. V., Carlson, A., Chang, K.-M., Malave, V. L., Mason, R. A., & Just, M. A. (2008) · Science · doi:10.1126/science.1152876 · Cited by 1,180
A Population-Average, Landmark- and Surface-based (PALS) atlas of human cerebral cortex
Van Essen, D. C. (2005) · NeuroImage · doi:10.1016/j.neuroimage.2005.06.058 · Cited by 1,151
Kriegeskorte, N. (2015) · Annual Review of Vision Science · doi:10.1146/annurev-vision-082114-035447 · Cited by 1,093
A deep learning framework for neuroscience
Richards, B. A., Lillicrap, T. P., Beaudoin, P., Bengio, Y., Bogacz, R., Christensen, A., Clopath, C., Costa, R. P., de Berker, A., Ganguli, S., et al. (2019) · Nature Neuroscience · doi:10.1038/s41593-019-0520-2 · Cited by 1,027
Phonetic Feature Encoding in Human Superior Temporal Gyrus
Mesgarani, N., Cheung, C., Johnson, K., & Chang, E. F. (2014) · Science · doi:10.1126/science.1245994 · Cited by 993
Magnetoencephalography for Brain Electrophysiology and Imaging
Baillet, S. (2017) · Nature Neuroscience · doi:10.1038/nn.4504 · Cited by 992
Guclu, U., & van Gerven, M. A. J. (2015) · Journal of Neuroscience · doi:10.1523/jneurosci.5023-14.2015 · Cited by 961
HellaSwag: Can a Machine Really Finish Your Sentence?
Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., & Choi, Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1472 · Cited by 830
Cortical representation of the constituent structure of sentences
Pallier, C., Devauchelle, A.-D., & Dehaene, S. (2011) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1018711108 · Cited by 691
New method for fMRI investigations of language: defining ROIs functionally in individual subjects
Fedorenko, E., Hsieh, P.-J., Nieto-Castañón, A., Whitfield-Gabrieli, S., & Kanwisher, N. (2010) · Journal of Neurophysiology · doi:10.1152/jn.00032.2010 · Cited by 686
Kell, A. J. E., Yamins, D. L. K., Shook, E. N., Norman-Haignere, S. V., & McDermott, J. H. (2018) · Neuron · doi:10.1016/j.neuron.2018.03.044 · Cited by 544
If deep learning is the answer, what is the question?
Saxe, A., Nelli, S., & Summerfield, C. (2021) · Nature Reviews Neuroscience · doi:10.1038/s41583-020-00395-8 · Cited by 397
Seeing it all: Convolutional network layers map the function of the human visual system
Eickenberg, M., Gramfort, A., Varoquaux, G., & Thirion, B. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2016.10.001 · Cited by 338
Sensory–motor transformations for speech occur bilaterally
Cogan, G. B., Thesen, T., Carlson, C., Doyle, W., Devinsky, O., & Pesaran, B. (2014) · Nature · doi:10.1038/nature12935 · Cited by 273
Neural correlate of the construction of sentence meaning
Fedorenko, E., Scott, T. L., Brunner, P., Coon, W. G., Pritchett, B., Schalk, G., & Kanwisher, N. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1612132113 · Cited by 199
Lack of selectivity for syntax relative to word meanings throughout the language network
Fedorenko, E., Blank, I. A., Siegelman, M., & Mineroff, Z. (2020) · Cognition · doi:10.1016/j.cognition.2020.104348 · Cited by 170
Incorporating Context into Language Encoding Models for fMRI
Jain, S., & Huth, A. G. (2018) · doi:10.1101/327601 · Cited by 155
Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks
Loula, J., Baroni, M., & Lake, B. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5413 · Cited by 136
Aligning context-based statistical models of language with brain activity during reading
Wehbe, L., Vaswani, A., Knight, K., & Mitchell, T. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1030 · Cited by 95
Cited by
The neural architecture of language: Integrative modeling converges on predictive processing
Schrimpf, M., Blank, I. A., Tuckute, G., Kauf, C., Hosseini, E. A., Kanwisher, N., Tenenbaum, J. B., & Fedorenko, E. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2105646118 · Cited by 517
A hierarchy of linguistic predictions during natural language comprehension
Heilbron, M., Armeni, K., Schoffelen, J.-M., Hagoort, P., & de Lange, F. P. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2201968119 · Cited by 343
The neural architecture of language: Integrative modeling converges on predictive processing
(2020) · doi:10.1101/2020.06.26.174482 · Cited by 129
Anderson, A. J., Kiela, D., Binder, J. R., Fernandino, L., Humphries, C. J., Conant, L. L., Raizada, R. D. S., Grimm, S., & Lalor, E. C. (2021) · The Journal of Neuroscience · doi:10.1523/jneurosci.1152-20.2021 · Cited by 70
A hierarchy of linguistic predictions during natural language comprehension
(2020) · doi:10.1101/2020.12.03.410399 · Cited by 63
Metadata
- Authors
- Caucheteux, C., & King, J.-R.
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2020-07-04
- OpenAlex
- W3039556919
- Cited by
- 47
- References
- 38
- Type
- posted content
- Language
- en
- Open access
- green
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.