The DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
Emergent linguistic structure in artificial neural networks trained by self-supervision
Open accessAbstract
This paper explores the knowledge of linguistic structure learned by large artificial neural networks, trained via self-supervision, whereby the model simply tries to predict a masked word in a given context. Human language communication is via sequences of words, but language understanding requires constructing rich hierarchical structures that are never observed explicitly. The mechanisms for this have been a prime mystery of human language acquisition, while engineering work has mainly proceeded by supervised learning on treebanks of sentences hand labeled for this latent structure. However, we demonstrate that modern deep contextual language models learn major aspects of this structure, without any explicit supervision. We develop methods for identifying linguistic hierarchical structure emergent in artificial neural networks and demonstrate that components in these models focus on syntactic grammatical relationships and anaphoric coreference. Indeed, we show that a linear transformation of learned embeddings in these models captures parse tree distances to a surprising degree, allowing approximate reconstruction of the sentence tree structures normally assumed by linguists. These results help explain why these models have brought such large improvements across many language-understanding tasks.
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
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071
Self-citationDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 15,539
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
Self-citationShow, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Building a Large Annotated Corpus of English: The Penn Treebank
Marcus, M. (1993) · doi:10.21236/ada273556 · Cited by 7,405
Landauer, T. K., & Dumais, S. T. (1997) · Psychological Review · doi:10.1037/0033-295x.104.2.211 · Cited by 6,282
Learning Deep Architectures for AI
Bengio, Y. (2009) · now publishers, Inc. eBooks · doi:10.1561/9781601982957 · Cited by 4,941
Knowledge of Language: Its Nature, Origin, and Use.
Hornstein, N., & Chomsky, N. (1988) · The Philosophical Review · doi:10.2307/2185417 · Cited by 4,650
“Cloze Procedure”: A New Tool for Measuring Readability
Taylor, W. L. (1953) · Journalism Quarterly · doi:10.1177/107769905303000401 · Cited by 2,332
Early language acquisition: cracking the speech code
Kuhl, P. K. (2004) · Nature Reviews Neuroscience · doi:10.1038/nrn1533 · Cited by 2,291 · cited 1×
“H language communication is via sequences of words, canonically produced as a mainly continuous speech stream (1).”
BackgroundGenerating Typed Dependency Parses from Phrase Structure Parses
de Marneffe, M.-C., MacCartney, B., & Manning, C. D. (2006) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/3wtkaidk6ea8 · Cited by 2,258
Self-citationHead-Driven Statistical Models for Natural Language Parsing
Collins, M. (2003) · Computational Linguistics · doi:10.1162/089120103322753356 · Cited by 1,826
A Fast and Accurate Dependency Parser using Neural Networks
Chen, D., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1082 · Cited by 1,795
Self-citationWhat Does BERT Look at? An Analysis of BERT’s Attention
Clark, K., Khandelwal, U., Levy, O., & Manning, C. D. (2019) · Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w19-4828 · Cited by 1,373
Self-citationUniversal Dependencies v1: A Multilingual Treebank Collection
Nivre, J., de Marneffe, M.-C., Ginter, F., Goldberg, Y., Hajič, J., Manning, C. D., McDonald, R., Petrov, S., Pyysalo, S., Silveira, N., et al. (2016) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/2hnj7od8afy8 · Cited by 1,028
Self-citationAssessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
Linzen, T., Dupoux, E., & Goldberg, Y. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00115 · Cited by 737
Tenney, I., Xia, P., Chen, B., Wang, A., Poliak, A., McCoy, R. T., Kim, N., Van Durme, B., Bowman, S. R., Das, D., et al. (2019) · arXiv · doi:10.48550/arxiv.1905.06316 · Cited by 698
Deep Biaffine Attention for Neural Dependency Parsing
Atmani, M., & Lafourcade, M. (2016) · arXiv (Cornell University) · doi:10.4230/oasics.ldk.2021.24 · Cited by 693
What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties
Conneau, A., Kruszewski, G., Lample, G., Barrault, L., & Baroni, M. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1198 · Cited by 657
Linguistic Knowledge and Transferability of Contextual Representations
Liu, N. F., Gardner, M., Belinkov, Y., Peters, M. E., & Smith, N. A. (2019) · Proceedings of the 2019 Conference of the North · doi:10.18653/v1/n19-1112 · Cited by 621
(2012) · Cited by 618
Proceedings of the International Joint Conference on Neural Networks (IJCNN) 2005
(2005) · Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. · doi:10.1109/ijcnn.2005.1556327 · Cited by 553
Bock, K., & Miller, C. A. (1991) · Cognitive Psychology · doi:10.1016/0010-0285(91)90003-7 · Cited by 529
Deep Biaffine Attention for Neural Dependency ParsingPreprint
Dozat, T., & Manning, C. D. (2016) · arXiv (Cornell University) · Cited by 515
Self-citationStanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task
Lee, H., Peirsman, Y., Chang, A. L. S., Chambers, N., Surdeanu, M., & Jurafsky, D. (2011) · Lirias · Cited by 504
Colorless Green Recurrent Networks Dream Hierarchically
Gulordava, K., Bojanowski, P., Grave, E., Linzen, T., & Baroni, M. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1108 · Cited by 465
Poverty of the Stimulus Revisited
Berwick, R. C., Pietroski, P., Yankama, B., & Chomsky, N. (2011) · Cognitive Science · doi:10.1111/j.1551-6709.2011.01189.x · Cited by 447
Dissecting Contextual Word Embeddings: Architecture and Representation
Peters, M., Neumann, M., Zettlemoyer, L., & Yih, W.-T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1179 · Cited by 434
Linguistically-Informed Self-Attention for Semantic Role Labeling
Strubell, E., Verga, P., Andor, D., Weiss, D., & McCallum, A. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1548 · Cited by 406
Assessing BERT's Syntactic Abilities
Goldberg, Y. (2019) · arXiv · doi:10.48550/arxiv.1901.05287 · Cited by 385
Targeted Syntactic Evaluation of Language Models
Marvin, R., & Linzen, T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1151 · Cited by 334 · cited 1×
“Subsequent work has evaluated models on more challenging sentences where potential confounds are removed (25), evaluated models on other grammatical phenomena such as reflexive anaphora (26), evaluated models that explicitly model hierarchy (27), and evaluated BERT on agreement across attractors (28).”
BackgroundWhat do Neural Machine Translation Models Learn about Morphology?
Belinkov, Y., Durrani, N., Dalvi, F., Sajjad, H., & Glass, J. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1080 · Cited by 307
Does String-Based Neural MT Learn Source Syntax?
Shi, X., Padhi, I., & Knight, K. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1159 · Cited by 300
Action Recognition using Visual Attention
Sharma, S., Kiros, R., & Salakhutdinov, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.04119 · Cited by 298
Tree-to-Sequence Attentional Neural Machine Translation
Eriguchi, A., Hashimoto, K., & Tsuruoka, Y. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1078 · Cited by 265
What you can cram into a single vector: Probing sentence embeddings for linguistic properties
Conneau, A., Kruszewski, G., Lample, G., Barrault, L., & Baroni, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.01070 · Cited by 263
Zhang, K., & Bowman, S. R. (2018) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/w18-5448 · Cited by 212
Perception viewed as an inverse problem
Pizlo, Z. (2001) · Vision Research · doi:10.1016/s0042-6989(01)00173-0 · Cited by 195
SemEval 2014 Task 8: Broad-Coverage Semantic Dependency Parsing
Oepen, S., Kuhlmann, M., Miyao, Y., Zeman, D., Flickinger, D., Hajic, J., Ivanova, A., & Zhang, Y. (2014) · Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) · doi:10.3115/v1/s14-2008 · Cited by 167
Just Say No to Single Embeddings: Why Your AI Needs Multiple Perspectives
Coenen, A., Reif, E., Yuan, A., Kim, B., Pearce, A., Viégas, F., & WATTENBERG, M. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.02715 · Cited by 163
LSTMs Can Learn Syntax-Sensitive Dependencies Well, But Modeling Structure Makes Them Better
Kuncoro, A., Dyer, C., Hale, J., Yogatama, D., Clark, S. C., & Blunsom, P. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-1132 · Cited by 134
An on-line algorithm for dynamic reinforcement learning and planning in reactive environments
Schmidhuber, J. (1990) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1990.137723 · Cited by 130
Deep RNNs Encode Soft Hierarchical Syntax
Blevins, T., Levy, O., & Zettlemoyer, L. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-2003 · Cited by 123
Self-citation5 Grammatical Illusions and Selective Fallibility in Real-Time Language Comprehension
Phillips, C., WAGERS, M. W., & Lau, E. F. (2011) · Syntax and semantics · doi:10.1108/s0092-4563(2011)0000037009 · Cited by 114
Adaptive Road Following using Self-Supervised Learning and Reverse Optical Flow
Lieb, D., Lookingbill, A., & Thrun, S. (2005) · Robotics: Science and Systems · doi:10.15607/rss.2005.i.036 · Cited by 110
Syntax-Directed Attention for Neural Machine Translation
Chen, K., Wang, R., Utiyama, M., Sumita, E., & Zhao, T. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11910 · Cited by 99
Reisinger, D., Rudinger, R., Ferraro, F., Harman, C., Rawlins, K., & Durme, B. V. (2015) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00152 · Cited by 74
What’s in an Embedding? Analyzing Word Embeddings through Multilingual Evaluation
Köhn, A. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1246 · Cited by 69
Zhang, K. W., & Bowman, S. R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.10040 · Cited by 45
Understanding Learning Dynamics Of Language Models with SVCCA
Saphra, N., & Lopez, A. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1329 · Cited by 31
Cited by
A primer in BERTology: What we know about how BERT works
Rogers, A., Kovaleva, O., & Rumshisky, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00349 · Cited by 1,552
Pre-trained models: Past, present and future
Han, X., Zhang, Z., Ding, N., Gu, Y., Liu, X., Huo, Y., Qiu, J., Yao, Y., Zhang, A., Zhang, L., et al. (2021) · AI Open · doi:10.1016/j.aiopen.2021.08.002 · Cited by 994
Shared computational principles for language processing in humans and deep language models
Goldstein, A., Zada, Z., Buchnik, E., Schain, M., Price, A., Aubrey, B., Nastase, S. A., Feder, A., Emanuel, D., Cohen, A., et al. (2022) · Nature Neuroscience · doi:10.1038/s41593-022-01026-4 · Cited by 447
Self-citationA 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
More than a Feeling: Accuracy and Application of Sentiment Analysis
Hartmann, J., Heitmann, M., Siebert, C., & Schamp, C. (2023) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2022.05.005 · Cited by 356
Metadata
- Authors
- Manning, C. D., Clark, K., Hewitt, J., Khandelwal, U., & Levy, O.
- Venue
- Proceedings of the National Academy of Sciences
- Published
- 2020-06-03
- Volume
- 117
- Issue
- 48
- Pages
- 30046-30054
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- OpenAlex
- W3031914912
- Cited by
- 339
- References
- 63
- FWCI
- 18.37
- Type
- journal article
- 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.