---
title: "Language acquisition: do children and language models follow similar learning stages? — Evanson 2023"
description: "The authors test whether neural language models pass through similar stages. 47 references, cited by 33 papers here."
authors: ["Linnea Evanson", "Yair Lakretz", "Jean-Rémi King"]
year: 2023
venue: "arXiv:2306.03586"
source: "https://arxiv.org/abs/2306.03586"
doi: "10.48550/arxiv.2306.03586"
arxiv: "2306.03586"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/evanson-2023-language-acquisition-children-language-models/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/evanson-2023-language-acquisition-children-language-models/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/6/) / Language acquisition: do children and language models follow similar learning stages?

# Language acquisition: do children and language models follow similar learning stages?

**Authors:** Linnea Evanson, [Yair Lakretz](https://md.research.elamur.ai/free/en/authors/yair-lakretz/) and Jean-Rémi King · **Year:** 2023 · **Venue:** arXiv:2306.03586 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2306.03586) · [PDF](https://arxiv.org/pdf/2306.03586) · [DOI 10.48550/arxiv.2306.03586](https://doi.org/10.48550/arxiv.2306.03586) · [arXiv 2306.03586](https://arxiv.org/abs/2306.03586)

**Citations:** 33 in our library, of the 140,884 papers whose bibliographies we read

## Summary

Children acquire language in a consistent order: first sounds, then words, and later increasingly complex syntax. The computational principles that give rise to this order remain unclear. The authors test whether neural language models pass through similar stages. To do so, they trained 48 GPT-2 models from scratch on the WikiText103 corpus, each with a different random seed. Every 100 training steps, the models were evaluated on 96 zero-shot probes selected from BLiMP, Zorro and BIG-Bench. Each probe is a pair of sentences: a grammatical one and a similar ungrammatical one. A model passes a probe if it assigns a higher probability to the grammatical sentence. The models' trajectories were compared with data from Friedmann et al. (2021) on the spontaneous speech of 54 children. It turned out that different models acquire skills in a similar sequence. At the same time, learning proceeds in parallel: even "late" skills begin to improve from the very first steps, only more slowly. Some of the stages coincide in children and models, but not all. This work makes it possible to test hypotheses about language acquisition on artificial models, in particular within the debate between nativism and empiricism.

## Key points

- **Data and models:** 48 12-layer GPT-2 models were trained on WikiText103 (about 181 MB). For comparison, a pretrained GPT-2 large, trained on roughly 40 GB of text, was used. It performs above chance on 93 of the 96 probes, whereas the authors' models do so on only 64 (66%).
- **Systematicity:** acquisition time was defined as the point at which a model reaches 90% of its final accuracy on a probe. The order in which probes are acquired correlates across models with R = 0.743 (p \< 0.001, permutation test).
- **Parallel learning:** in 95% of the probes, accuracy already increases within the first 300 steps. Early, intermediate and late groups of probes differ in learning rate, as confirmed by a one-way ANOVA.
- **Comparison with children:** the data cover 54 Hebrew-speaking children aged 18–71 months. Three stages were compared: simple sentences with SV order, Wh-questions, and relative clauses.
- **Limitations:** only one architecture and one corpus were studied. Children and models were assessed with different protocols, and only three syntactic features could be compared directly. On the most difficult probes (incongruent attractors), the models appear to rely on heuristics and more often choose the plural verb.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

Topics: [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · [🧒 Psycholinguistics & language acquisition](https://md.research.elamur.ai/free/en/topics/psycholinguistics/)

## Cite

Cite as: Linnea Evanson, Yair Lakretz and Jean-Rémi King. 2023. Language acquisition: do children and language models follow similar learning stages?. arXiv:2306.03586.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{evanson2023language,
  title = {{Language acquisition: do children and language models follow similar learning stages?}},
  author = {Linnea Evanson, Yair Lakretz and Jean-Rémi King},
  year = {2023},
  doi = {10.48550/arxiv.2306.03586},
  eprint = {2306.03586},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2306.03586}
}
```

- [← previous Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing](https://md.research.elamur.ai/free/en/papers/jung-2023-impossible-distillation-low-quality-model/)
- [next → DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models](https://md.research.elamur.ai/free/en/papers/gong-2023-diffuseq-v2-bridging-discrete-continuous/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/6/)

## References

47 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Elika Bergelson and Daniel Swingley. 2012. At 6–9 months, human infants know the meanings of many common nouns. Proceedings of the National Academy of Sciences, 109:3253–3258. [find](https://scholar.google.com/scholar?q=Elika+Bergelson+and+Daniel+Swingley%2E+2012%2E+At+6%E2%80%939+months%2C+human+infants+know+the+meanings+of+many+common+nouns%2E+Proceedings+of+the+National+Academy+of+Sciences%2C+109%3A3253%E2%80%933258%2E)
2. Samuel R. Bowman and George Dahl. 2021. What will it take to fix benchmarking in natural language understanding? Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4843–4855. [find](https://scholar.google.com/scholar?q=Samuel+R%2E+Bowman+and+George+Dahl%2E+2021%2E+What+will+it+take+to+fix+benchmarking+in+natural+language+understanding%3F+Proceedings+of+the+2021+Conference+of+the+North+American+Chapter+of+the+Association+for)
3. Charlotte Caucheteux, Alexandre Gramfort, and Jean-Rémi King. 2023. Evidence of a predictive coding hierarchy in the human brain listening to speech. Nature Human Behaviour, pages 1–12. [find](https://scholar.google.com/scholar?q=Charlotte+Caucheteux%2C+Alexandre+Gramfort%2C+and+Jean%2DR%C3%A9mi+King%2E+2023%2E+Evidence+of+a+predictive+coding+hierarchy+in+the+human+brain+listening+to+speech%2E+Nature+Human+Behaviour%2C+pages+1%E2%80%9312%2E)
4. Charlotte Caucheteux and Jean Rémi King. 2022. Brains and algorithms partially converge in natural language processing. Communications Biology, 5(1). [find](https://scholar.google.com/scholar?q=Charlotte+Caucheteux+and+Jean+R%C3%A9mi+King%2E+2022%2E+Brains+and+algorithms+partially+converge+in+natural+language+processing%2E+Communications+Biology%2C+5%281%29%2E)
5. Tyler A. Chang and Benjamin K. Bergen. 2022. Word acquisition in neural language models. Transactions of the Association for Computational Linguistics, 10:1–16. [find](https://scholar.google.com/scholar?q=Tyler+A%2E+Chang+and+Benjamin+K%2E+Bergen%2E+2022%2E+Word+acquisition+in+neural+language+models%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+10%3A1%E2%80%9316%2E)
6. Nick Chater and Morten H Christiansen. 2018. Language acquisition as skill learning. Current opinion in behavioral sciences, 21:205–208. [find](https://scholar.google.com/scholar?q=Nick+Chater+and+Morten+H+Christiansen%2E+2018%2E+Language+acquisition+as+skill+learning%2E+Current+opinion+in+behavioral+sciences%2C+21%3A205%E2%80%93208%2E)
7. Noam Chomsky. 1959. Review of verbal behavior. 35(1):26–58. Publisher: Linguistic Society of America. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2E+1959%2E+Review+of+verbal+behavior%2E+35%281%29%3A26%E2%80%9358%2E+Publisher%3A+Linguistic+Society+of+America%2E)
8. Noam Chomsky. 1971. Problems of Knowledge and Freedom. New York,: W.W. Norton. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2E+1971%2E+Problems+of+Knowledge+and+Freedom%2E+New+York%2C%3A+W%2EW%2E+Norton%2E)
9. Alexander Clark. 2002. Unsupervised language acquisition: Theory and practice. arXiv preprint cs/0212024. [find](https://scholar.google.com/scholar?q=Alexander+Clark%2E+2002%2E+Unsupervised+language+acquisition%3A+Theory+and+practice%2E+arXiv+preprint+cs%2F0212024%2E)
10. Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova Google, and AI Language. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langu… [our card](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/)
11. Emmanuel Dupoux. 2018. Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner. Cognition, 173:43–59. [find](https://scholar.google.com/scholar?q=Emmanuel+Dupoux%2E+2018%2E+Cognitive+science+in+the+era+of+artificial+intelligence%3A+A+roadmap+for+reverse%2Dengineering+the+infant+language%2Dlearner%2E+Cognition%2C+173%3A43%E2%80%9359%2E)
12. Naama Friedmann, Adriana Belletti, and Luigi Rizzi. 2021. Growing trees: The acquisition of the left periphery. Glossa: a journal of general linguistics, 39(1). [find](https://scholar.google.com/scholar?q=Naama+Friedmann%2C+Adriana+Belletti%2C+and+Luigi+Rizzi%2E+2021%2E+Growing+trees%3A+The+acquisition+of+the+left+periphery%2E+Glossa%3A+a+journal+of+general+linguistics%2C+39%281%29%2E)
13. Naama Friedmann and Julia Reznick. 2021. Stages rather than ages in the acquisition of movement structures: Data from sentence repetition and 27696 spontaneous clauses. Glossa: a journal of general linguistics, 39(1). [our card](https://md.research.elamur.ai/free/en/papers/friedmann-2021-stages-rather-than-ages-acquisition/)
14. Kristina Gulordava, Piotr Bojanowski, Edouard Grave, Tal Linzen, and Marco Baroni. 2018. Colorless green recurrent networks dream hierarchically. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume… [our card](https://md.research.elamur.ai/free/en/papers/gulordava-2018-colorless-green-recurrent-networks-dream/)
15. John Hewitt and Christopher D Manning. 2019. A structural probe for finding syntax in word representations. In 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), pages 4129–… [our card](https://md.research.elamur.ai/free/en/papers/hewitt-2019-structural-probe-finding-syntax-word/)
16. Philip Huebner. 2022. Unmasked. [https://github.com/phueb/UnMasked](https://github.com/phueb/UnMasked). (Accessed 2023/05/24). [↗](https://github.com/phueb/UnMasked)
17. Philip A Huebner, Elior Sulem, Cynthia Fisher, and Dan Roth. 2021. BabyBERTa : Learning More Grammar With Small-Scale Child-Directed Language. Proceedings of the 25th Conference on Computational Natural Language Learning, pages 624–646. [our card](https://md.research.elamur.ai/free/en/papers/huebner-2021-babyberta-learning-more-grammar-small/)
18. Shailee Jain and Alexander Huth. 2018. Incorporating context into language encoding models for fmri. In Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Shailee+Jain+and+Alexander+Huth%2E+2018%2E+Incorporating+context+into+language+encoding+models+for+fmri%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+31%2E+Curran+Associates%2C+Inc%2E)
19. Ganesh Jawahar, Benoît Sagot, and Djamé Seddah. 2019. What does bert learn about the structure of language? Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3651–3657. [our card](https://md.research.elamur.ai/free/en/papers/jawahar-2019-what-does-bert-learn-about/)
20. Jaap Jumelet, Willem Zuidema, and Dieuwke Hupkes. 2019. Analysing neural language models: Contextual decomposition reveals default reasoning in number and gender assignment. Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 1–11. [find](https://scholar.google.com/scholar?q=Jaap+Jumelet%2C+Willem+Zuidema%2C+and+Dieuwke+Hupkes%2E+2019%2E+Analysing+neural+language+models%3A+Contextual+decomposition+reveals+default+reasoning+in+number+and+gender+assignment%2E+Proceedings+of+the+23rd+Co)
21. Fred Karlsson. 2007. Constraints on multiple center-embedding of clauses. Journal of Linguistics, 43(2):365–392. [find](https://scholar.google.com/scholar?q=Fred+Karlsson%2E+2007%2E+Constraints+on+multiple+center%2Dembedding+of+clauses%2E+Journal+of+Linguistics%2C+43%282%29%3A365%E2%80%93392%2E)
22. Eugene Kharitonov and Rahma Chaabouni. 2020. What they do when in doubt: a study of inductive biases in seq2seq learners. arXiv:2006.14953. — [arXiv:2006.14953](https://arxiv.org/abs/2006.14953) [find](https://scholar.google.com/scholar?q=Eugene+Kharitonov+and+Rahma+Chaabouni%2E+2020%2E+What+they+do+when+in+doubt%3A+a+study+of+inductive+biases+in+seq2seq+learners%2E+arXiv%3A2006%2E14953%2E+%E2%80%94+%5BarXiv%3A2006%2E14953%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2006%2E14953%29)
23. Oren Kolodny, Arnon Lotem, and Shimon Edelman. 2015. Learning a generative probabilistic grammar of experience: A process-level model of language acquisition. Cognitive Science, 39(2):227–267. [find](https://scholar.google.com/scholar?q=Oren+Kolodny%2C+Arnon+Lotem%2C+and+Shimon+Edelman%2E+2015%2E+Learning+a+generative+probabilistic+grammar+of+experience%3A+A+process%2Dlevel+model+of+language+acquisition%2E+Cognitive+Science%2C+39%282%29%3A227%E2%80%93267%2E)
24. Patricia K. Kuhl. 2004. Early language acquisition: cracking the speech code. Nature Reviews Neuroscience, 5:831–843. [find](https://scholar.google.com/scholar?q=Patricia+K%2E+Kuhl%2E+2004%2E+Early+language+acquisition%3A+cracking+the+speech+code%2E+Nature+Reviews+Neuroscience%2C+5%3A831%E2%80%93843%2E)
25. Patricia K Kuhl, Erica Stevens, Akiko Hayashi, Toshisada Deguchi, Shigeru Kiritani, and Paul Iverson. 2006. Fast-track report infants show a facilitation effect for native language phonetic perception between 6 and 12 months. Developmental Science, 9:13–21. [find](https://scholar.google.com/scholar?q=Patricia+K+Kuhl%2C+Erica+Stevens%2C+Akiko+Hayashi%2C+Toshisada+Deguchi%2C+Shigeru+Kiritani%2C+and+Paul+Iverson%2E+2006%2E+Fast%2Dtrack+report+infants+show+a+facilitation+effect+for+native+language+phonetic+perception)
26. Stewart M McCauley and Morten H Christiansen. 2019. Language learning as language use: A cross-linguistic model of child language development. Psychological review, 126(1):1. [find](https://scholar.google.com/scholar?q=Stewart+M+McCauley+and+Morten+H+Christiansen%2E+2019%2E+Language+learning+as+language+use%3A+A+cross%2Dlinguistic+model+of+child+language+development%2E+Psychological+review%2C+126%281%29%3A1%2E)
27. R Thomas McCoy, Robert Frank, and Tal Linzen. 2020. Does syntax need to grow on trees? sources of hierarchical inductive bias in sequence-to-sequence networks. Transactions of the Association for Computational Linguistics, 8:125–140. [our card](https://md.research.elamur.ai/free/en/papers/mccoy-2020-does-syntax-need-grow-trees/)
28. Jacques Mehler, Peter Jusczyk, Ghislaine Lambertz, Nilofar Halsted, Josiane Bertoncini, and Claudine Amiel-Tison. 1988. A precursor of language acquisition in young infants. Cognition, 29:143–178. [find](https://scholar.google.com/scholar?q=Jacques+Mehler%2C+Peter+Jusczyk%2C+Ghislaine+Lambertz%2C+Nilofar+Halsted%2C+Josiane+Bertoncini%2C+and+Claudine+Amiel%2DTison%2E+1988%2E+A+precursor+of+language+acquisition+in+young+infants%2E+Cognition%2C+29%3A143%E2%80%93178%2E)
29. Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. Pointer sentinel mixture models. arXiv:1609.07843. [our card](https://md.research.elamur.ai/free/en/papers/merity-2016-pointer-sentinel-mixture-models/)
30. Patricia K. Kuhl, Karen A. Williams, Francisco Lac-erda, Kenneth N. Stevens, and Bjorn Lindblom. 1992. Linguistic experience alters phonetic perception in infants by 6 months of age. Science, 255:606–608. [find](https://scholar.google.com/scholar?q=Patricia+K%2E+Kuhl%2C+Karen+A%2E+Williams%2C+Francisco+Lac%2Derda%2C+Kenneth+N%2E+Stevens%2C+and+Bjorn+Lindblom%2E+1992%2E+Linguistic+experience+alters+phonetic+perception+in+infants+by+6+months+of+age%2E+Science%2C+255%3A606%E2%80%93)
31. Thierry Nazzi, Peter W. Jusczyk, and Elizabeth K. Johnson. 2000. Language discrimination by english-learning 5-month-olds: Effects of rhythm and familiarity. Journal of Memory and Language, 43:1–19. [find](https://scholar.google.com/scholar?q=Thierry+Nazzi%2C+Peter+W%2E+Jusczyk%2C+and+Elizabeth+K%2E+Johnson%2E+2000%2E+Language+discrimination+by+english%2Dlearning+5%2Dmonth%2Dolds%3A+Effects+of+rhythm+and+familiarity%2E+Journal+of+Memory+and+Language%2C+43%3A1%E2%80%9319%2E)
32. Yair Lakretz, Théo Desbordes, Dieuwke Hupkes, and Stanislas Dehaene. 2021a. Causal transformers perform below chance on recursive nested constructions, unlike humans. arXiv:2110.07240. — [arXiv:2110.07240](https://arxiv.org/abs/2110.07240) [find](https://scholar.google.com/scholar?q=Yair+Lakretz%2C+Th%C3%A9o+Desbordes%2C+Dieuwke+Hupkes%2C+and+Stanislas+Dehaene%2E+2021a%2E+Causal+transformers+perform+below+chance+on+recursive+nested+constructions%2C+unlike+humans%2E+arXiv%3A2110%2E07240%2E+%E2%80%94+%5BarXiv%3A2110%2E0)
33. Alexandre Pasquiou, Yair Lakretz, John Hale, Bertrand Thirion, and Christophe Pallier. 2022. Neural language models are not born equal to fit brain data, but training helps. In ICML 2022-39th International Conference on Machine Learning, page 18. [find](https://scholar.google.com/scholar?q=Alexandre+Pasquiou%2C+Yair+Lakretz%2C+John+Hale%2C+Bertrand+Thirion%2C+and+Christophe+Pallier%2E+2022%2E+Neural+language+models+are+not+born+equal+to+fit+brain+data%2C+but+training+helps%2E+In+ICML+2022%2D39th+Internat)
34. Yair Lakretz, Dieuwke Hupkes, Alessandra Vergallito, Marco Marelli, Marco Baroni, and Stanislas Dehaene. 2021b. Mechanisms for handling nested dependencies in neural-network language models and humans. Cognition, 213:104699. Special Issue in Honour of Jacques Mehler, Cognition’s founding editor. [find](https://scholar.google.com/scholar?q=Yair+Lakretz%2C+Dieuwke+Hupkes%2C+Alessandra+Vergallito%2C+Marco+Marelli%2C+Marco+Baroni%2C+and+Stanislas+Dehaene%2E+2021b%2E+Mechanisms+for+handling+nested+dependencies+in+neural%2Dnetwork+language+models+and+humans)
35. Yair Lakretz, German Kruszewski, Theo Desbordes, Dieuwke Hupkes, Stanislas Dehaene, and Marco Baroni. 2019. The emergence of number and syntax units in LSTM language models. Association for Computational Linguistics, pages 11–20. [our card](https://md.research.elamur.ai/free/en/papers/lakretz-2019-emergence-number-syntax-units-lstm/)
36. Marvin Lavechin, Maureen De Seyssel, Hadrien Titeux, Hervé Bredin, Guillaume Wisniewski, Alejandrina Cristia, and Emmanuel Dupoux. 2022. Statistical learning bootstraps early language acquisition. PsyArXiv. [find](https://scholar.google.com/scholar?q=Marvin+Lavechin%2C+Maureen+De+Seyssel%2C+Hadrien+Titeux%2C+Herv%C3%A9+Bredin%2C+Guillaume+Wisniewski%2C+Alejandrina+Cristia%2C+and+Emmanuel+Dupoux%2E+2022%2E+Statistical+learning+bootstraps+early+language+acquisition%2E+Psy)
37. Tal Linzen, Emmanuel Dupoux, and Yoav Goldberg. 2016. Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies. Transactions of the Association for Computational Linguistics, 4:521– 535. [our card](https://md.research.elamur.ai/free/en/papers/linzen-2016-assessing-ability-lstms-learn-syntax/)
38. Christopher D. Manning, Kevin Clark, John Hewitt, Urvashi Khandelwal, and Omer Levy. 2020. Emergent linguistic structure in artificial neural networks trained by self-supervision. Proceedings of the National Academy of Sciences of the United States of America, 117:30046–30054. [find](https://scholar.google.com/scholar?q=Christopher+D%2E+Manning%2C+Kevin+Clark%2C+John+Hewitt%2C+Urvashi+Khandelwal%2C+and+Omer+Levy%2E+2020%2E+Emergent+linguistic+structure+in+artificial+neural+networks+trained+by+self%2Dsupervision%2E+Proceedings+of+the+N)
39. Reiko Mazuka, Yvonne Cao, Emmanuel Dupoux, and Anne Christophe. 2011. The development of a phonological illusion: A cross-linguistic study with japanese and french infants. Developmental Science, 14:693–699. [find](https://scholar.google.com/scholar?q=Reiko+Mazuka%2C+Yvonne+Cao%2C+Emmanuel+Dupoux%2C+and+Anne+Christophe%2E+2011%2E+The+development+of+a+phonological+illusion%3A+A+cross%2Dlinguistic+study+with+japanese+and+french+infants%2E+Developmental+Science%2C+14%3A6)
40. Alexandre Pasquiou, Yair Lakretz, Bertrand Thirion, and Christophe Pallier. 2023. Information-restricted neural language models reveal different brain regions’ sensitivity to semantics, syntax and context. arXiv:2302.14389. — [arXiv:2302.14389](https://arxiv.org/abs/2302.14389) [find](https://scholar.google.com/scholar?q=Alexandre+Pasquiou%2C+Yair+Lakretz%2C+Bertrand+Thirion%2C+and+Christophe+Pallier%2E+2023%2E+Information%2Drestricted+neural+language+models+reveal+different+brain+regions%E2%80%99+sensitivity+to+semantics%2C+syntax+and+con)
41. Yada Pruksachatkun, Phil Yeres, Haokun Liu, Jason Phang, Phu Mon Htut, Alex Wang, Ian Tenney, and Samuel R. Bowman. 2020. jiant: A software toolkit for research on general-purpose text understanding models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: S… [find](https://scholar.google.com/scholar?q=Yada+Pruksachatkun%2C+Phil+Yeres%2C+Haokun+Liu%2C+Jason+Phang%2C+Phu+Mon+Htut%2C+Alex+Wang%2C+Ian+Tenney%2C+and+Samuel+R%2E+Bowman%2E+2020%2E+jiant%3A+A+software+toolkit+for+research+on+general%2Dpurpose+text+understanding+m)
42. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. Semantic Scholar. (Accessed 2023-05-04). [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+2019%2E+Language+Models+are+Unsupervised+Multitask+Learners%2E+Semantic+Scholar%2E+%28Accessed+2023%2D05%2D04%29%2E)
43. Rushen Shi, Janet F Werker, and James L Morgan. 1999. Newborn infants’ sensitivity to perceptual cues to lexical and grammatical words. Cognition, 72:B11– B21. [find](https://scholar.google.com/scholar?q=Rushen+Shi%2C+Janet+F+Werker%2C+and+James+L+Morgan%2E+1999%2E+Newborn+infants%E2%80%99+sensitivity+to+perceptual+cues+to+lexical+and+grammatical+words%2E+Cognition%2C+72%3AB11%E2%80%93+B21%2E)
44. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, et al. 2022. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv 2206.04615. [our card](https://md.research.elamur.ai/free/en/papers/srivastava-2022-imitation-game-quantifying-extrapolating-capabilities/)
45. Ruth Tincoff and Peter W. Jusczyk. 1999. Some beginnings of word comprehension in 6-month-olds. Psychological Science, 10:172–175. [find](https://scholar.google.com/scholar?q=Ruth+Tincoff+and+Peter+W%2E+Jusczyk%2E+1999%2E+Some+beginnings+of+word+comprehension+in+6%2Dmonth%2Dolds%2E+Psychological+Science%2C+10%3A172%E2%80%93175%2E)
46. Mariya Toneva and Leila Wehbe. 2019. Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain). In Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc. the linguistic stage 2, and, as it is part of the BIG-Be… [find](https://scholar.google.com/scholar?q=Mariya+Toneva+and+Leila+Wehbe%2E+2019%2E+Interpreting+and+improving+natural%2Dlanguage+processing+%28in+machines%29+with+natural+language%2Dprocessing+%28in+the+brain%29%2E+In+Advances+in+Neural+Information+Processing+)
47. Alex Warstadt and Samuel R Bowman. 2022. What artificial neural networks can tell us about human language acquisition. arXiv:2208.07998. [our card](https://md.research.elamur.ai/free/en/papers/warstadt-2022-artificial-neural-networks-tell-us/)