---
title: "How poor is the stimulus? Evaluating hierarchical generalization in neural networks — Yedetore 2023"
description: "The authors test whether this requires an innate bias toward hierarchy or whether the signals in child-directed… 60 references, cited by 27 papers here."
authors: ["Aditya Yedetore", "Tal Linzen", "Robert Frank", "R. Thomas McCoy"]
year: 2023
venue: "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2023.acl-long.521/"
doi: "10.18653/v1/2023.acl-long.521"
arxiv: "2301.11462"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yedetore-2023-how-poor-is-stimulus-evaluating/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yedetore-2023-how-poor-is-stimulus-evaluating/)

[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/) / How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech

# How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech

**Authors:** Aditya Yedetore, [Tal Linzen](https://md.research.elamur.ai/free/en/authors/tal-linzen/), [Robert Frank](https://md.research.elamur.ai/free/en/authors/robert-frank/) and [R. Thomas McCoy](https://md.research.elamur.ai/free/en/authors/r-thomas-mccoy/) · **Year:** 2023 · **Venue:** Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2023.acl-long.521/) · [PDF](https://aclanthology.org/2023.acl-long.521.pdf) · [DOI 10.18653/v1/2023.acl-long.521](https://doi.org/10.18653/v1/2023.acl-long.521) · [arXiv 2301.11462](https://arxiv.org/abs/2301.11462)

**Citations:** [27](https://md.research.elamur.ai/free/en/papers/yedetore-2023-how-poor-is-stimulus-evaluating/cited-by/) in our library, of the 140,884 papers whose bibliographies we read

## Summary

Children learning syntax reliably favor rules based on hierarchical structure rather than on linear order. The authors test whether this requires an innate bias toward hierarchy or whether the signals in child-directed speech alone are sufficient. To do so, they trained LSTMs and Transformers, i.e., architectures without a built-in hierarchical bias, on English data from CHILDES. In size and character, these data are close to what a child actually hears. The test phenomenon chosen was English yes/no questions. The two rules, hierarchical (HIERARCHICAL Q) and linear (LINEAR Q), make different predictions here only for rare complex sentences. The models were evaluated in two ways: by comparing sentence probabilities under the language model and by generating a question from a declarative sentence. Both architectures capture corpus statistics well, but they generalize based on linear word order and specific lexical items rather than on hierarchical structure. Thus, human-like acquisition of syntax from text alone likely requires stronger biases than those of standard neural networks. The work is important for the debate on the "poverty of the stimulus" in psycholinguistics.

## Key points

- **Corpus:** the North American English portion of CHILDES excluding the children's own utterances, about 9.6 million words. A 90/5/5 split into train/validation/test. Words occurring no more than twice in train were replaced with `<unk>` (this is 0.3% of tokens).
- **Models:** LSTM (2 layers, size 800) and Transformer (4 layers, 4 attention heads, size 800). Results are averaged over 10 runs with different seeds. The data and code are published in the `adityayedetore/lm-povstim-with-childes` repository on GitHub.
- **Language model quality:** test perplexity is 20.05 for the LSTM and 19.69 for the Transformer. A baseline 5-gram model with Kneser-Ney (KenLM) has 24.37. On the Zorro suite (24 syntactic tests based on BLiMP), most runs score above 0.9.
- **Main result:** in both experiments (relative acceptability and question generation), the models prefer the linear rule. In children, errors of this type are very rare.
- **Context and limitations:** in Wikipedia, sentences average about 25 words; in CHILDES, about 5. Models trained on large internet corpora have previously shown good results on this phenomenon. The modalities that the authors point to as sources of additional hierarchical cues (prosody, visual information, meaning, social interaction) are not taken into account in the study.

*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: [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [🧒 Psycholinguistics & language acquisition](https://md.research.elamur.ai/free/en/topics/psycholinguistics/)

## Cite

Cite as: Aditya Yedetore, Tal Linzen, Robert Frank and R. Thomas McCoy. 2023. How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{yedetore2023how,
  title = {{How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech}},
  author = {Aditya Yedetore, Tal Linzen, Robert Frank and R. Thomas McCoy},
  booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2023},
  doi = {10.18653/v1/2023.acl-long.521},
  eprint = {2301.11462},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2023.acl-long.521}
}
```

- [← previous Findings of the Second Shared Task on Multilingual Coreference Resolution](https://md.research.elamur.ai/free/en/papers/zabokrtsky-2023-findings-second-shared-task-multilingual/)
- [next → Nâbra: Syrian Arabic Dialects with Morphological Annotations](https://md.research.elamur.ai/free/en/papers/nayouf-2023-nabra-syrian-arabic-dialects-morphological/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/6/)

## References

60 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Omri Abend, Tom Kwiatkowski, Nathaniel J Smith, Sharon Goldwater, and Mark Steedman. 2017. Bootstrapping language acquisition. Cognition, 164:116– 143. [find](https://scholar.google.com/scholar?q=Omri+Abend%2C+Tom+Kwiatkowski%2C+Nathaniel+J+Smith%2C+Sharon+Goldwater%2C+and+Mark+Steedman%2E+2017%2E+Bootstrapping+language+acquisition%2E+Cognition%2C+164%3A116%E2%80%93+143%2E)
2. Gerry TM Altmann and Yuki Kamide. 1999. Incremental interpretation at verbs: Restricting the domain of subsequent reference. Cognition, 73(3):247–264. [find](https://scholar.google.com/scholar?q=Gerry+TM+Altmann+and+Yuki+Kamide%2E+1999%2E+Incremental+interpretation+at+verbs%3A+Restricting+the+domain+of+subsequent+reference%2E+Cognition%2C+73%283%29%3A247%E2%80%93264%2E)
3. Ben Ambridge, Caroline F Rowland, and Julian M Pine. 2008. Is structure dependence an innate constraint? New experimental evidence from children’s complex-question production. Cognitive Science, 32(1):222– 255. [find](https://scholar.google.com/scholar?q=Ben+Ambridge%2C+Caroline+F+Rowland%2C+and+Julian+M+Pine%2E+2008%2E+Is+structure+dependence+an+innate+constraint%3F+New+experimental+evidence+from+children%E2%80%99s+complex%2Dquestion+production%2E+Cognitive+Science%2C+32%281%29)
4. Robert Berwick, Paul Pietroski, Beracah Yankama, and Noam Chomsky. 2011. Poverty of the stimulus revisited. Cognitive science, 35:1207–42. [find](https://scholar.google.com/scholar?q=Robert+Berwick%2C+Paul+Pietroski%2C+Beracah+Yankama%2C+and+Noam+Chomsky%2E+2011%2E+Poverty+of+the+stimulus+revisited%2E+Cognitive+science%2C+35%3A1207%E2%80%9342%2E)
5. Rens Bod, Margaux Smets, et al. 2012. Empiricist solutions to nativist problems using tree-substitution grammars. Workshop on Computational Models of Language Acquisition and Loss: EACL. [find](https://scholar.google.com/scholar?q=Rens+Bod%2C+Margaux+Smets%2C+et+al%2E+2012%2E+Empiricist+solutions+to+nativist+problems+using+tree%2Dsubstitution+grammars%2E+Workshop+on+Computational+Models+of+Language+Acquisition+and+Loss%3A+EACL%2E)
6. Noam Chomsky. 1965. Aspects of the Theory of Syntax. The MIT Press. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2E+1965%2E+Aspects+of+the+Theory+of+Syntax%2E+The+MIT+Press%2E)
7. Noam Chomsky. 1980. Rules and Representations. Columbia University Press. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2E+1980%2E+Rules+and+Representations%2E+Columbia+University+Press%2E)
8. Alexander Clark and Rémi Eyraud. 2007. Polynomial identification in the limit of substitutable context-free languages. Journal of Machine Learning Research, 8(8). [find](https://scholar.google.com/scholar?q=Alexander+Clark+and+R%C3%A9mi+Eyraud%2E+2007%2E+Polynomial+identification+in+the+limit+of+substitutable+context%2Dfree+languages%2E+Journal+of+Machine+Learning+Research%2C+8%288%29%2E)
9. Alexander Clark and Shalom Lappin. 2010. Linguistic Nativism and the Poverty of the Stimulus. John Wiley & Sons. [find](https://scholar.google.com/scholar?q=Alexander+Clark+and+Shalom+Lappin%2E+2010%2E+Linguistic+Nativism+and+the+Poverty+of+the+Stimulus%2E+John+Wiley+%26+Sons%2E)
10. Stephen Crain and Mineharu Nakayama. 1987. Structure dependence in grammar formation. Language, pages 522–543. [find](https://scholar.google.com/scholar?q=Stephen+Crain+and+Mineharu+Nakayama%2E+1987%2E+Structure+dependence+in+grammar+formation%2E+Language%2C+pages+522%E2%80%93543%2E)
11. Jeffrey L Elman. 1991. Distributed representations, simple recurrent networks, and grammatical structure. Machine learning, 7(2):195–225. [find](https://scholar.google.com/scholar?q=Jeffrey+L+Elman%2E+1991%2E+Distributed+representations%2C+simple+recurrent+networks%2C+and+grammatical+structure%2E+Machine+learning%2C+7%282%29%3A195%E2%80%93225%2E)
12. Hartmut Fitz and Franklin Chang. 2017. Meaningful questions: The acquisition of auxiliary inversion in a connectionist model of sentence production. Cognition, 166:225–250. [find](https://scholar.google.com/scholar?q=Hartmut+Fitz+and+Franklin+Chang%2E+2017%2E+Meaningful+questions%3A+The+acquisition+of+auxiliary+inversion+in+a+connectionist+model+of+sentence+production%2E+Cognition%2C+166%3A225%E2%80%93250%2E)
13. Robert Frank and Donald Mathis. 2007. Transformational networks. Models of Human Language Acquisition, pages 22–27. [find](https://scholar.google.com/scholar?q=Robert+Frank+and+Donald+Mathis%2E+2007%2E+Transformational+networks%2E+Models+of+Human+Language+Acquisition%2C+pages+22%E2%80%9327%2E)
14. Lila R Gleitman, Kimberly Cassidy, Rebecca Nappa, Anna Papafragou, and John C Trueswell. 2005. Hard words. Language learning and development, 1(1):23– 64. [find](https://scholar.google.com/scholar?q=Lila+R+Gleitman%2C+Kimberly+Cassidy%2C+Rebecca+Nappa%2C+Anna+Papafragou%2C+and+John+C+Trueswell%2E+2005%2E+Hard+words%2E+Language+learning+and+development%2C+1%281%29%3A23%E2%80%93+64%2E)
15. 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. [our card](https://md.research.elamur.ai/free/en/papers/gulordava-2018-colorless-green-recurrent-networks-dream/)
16. John Hale. 2001. A probabilistic Earley parser as a psycholinguistic model. In Second Meeting of the North American Chapter of the Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/hale-2001-probabilistic-earley-parser-as-psycholinguistic/)
17. Betty Hart and Todd R Risley. 1995. Meaningful differences in the everyday experience of young American children. Paul H Brookes Publishing. [find](https://scholar.google.com/scholar?q=Betty+Hart+and+Todd+R+Risley%2E+1995%2E+Meaningful+differences+in+the+everyday+experience+of+young+American+children%2E+Paul+H+Brookes+Publishing%2E)
18. Kenneth Heafield. 2011. KenLM: Faster and smaller language model queries. In Proceedings of the Sixth Workshop on Statistical Machine Translation, pages 187–197, Edinburgh, Scotland. Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/heafield-2011-kenlm-faster-smaller-language-model/)
19. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735– 1780. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+J%C3%BCrgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+computation%2C+9%288%29%3A1735%E2%80%93+1780%2E)
20. Jennifer Hu, Jon Gauthier, Peng Qian, Ethan Wilcox, and Roger Levy. 2020. A systematic assessment of syntactic generalization in neural language models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1725–1744, Online. Association for Computational… [find](https://scholar.google.com/scholar?q=Jennifer+Hu%2C+Jon+Gauthier%2C+Peng+Qian%2C+Ethan+Wilcox%2C+and+Roger+Levy%2E+2020%2E+A+systematic+assessment+of+syntactic+generalization+in+neural+language+models%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+th)
21. Philip A. Huebner, Elior Sulem, Cynthia Fisher, and Dan Roth. 2021. BabyBERTa: Learning more grammar with small-scale child-directed language. In Proceedings of CoNLL. [our card](https://md.research.elamur.ai/free/en/papers/huebner-2021-babyberta-learning-more-grammar-small/)
22. Xuân-Nga Cao Kam, Iglika Stoyneshka, Lidiya Torny-ova, Janet D Fodor, and William G Sakas. 2008. Bigrams and the richness of the stimulus. Cognitive Science, 32(4):771–787. [find](https://scholar.google.com/scholar?q=Xu%C3%A2n%2DNga+Cao+Kam%2C+Iglika+Stoyneshka%2C+Lidiya+Torny%2Dova%2C+Janet+D+Fodor%2C+and+William+G+Sakas%2E+2008%2E+Bigrams+and+the+richness+of+the+stimulus%2E+Cognitive+Science%2C+32%284%29%3A771%E2%80%93787%2E)
23. Reinhard Kneser and Hermann Ney. 1995. Improved backing-off for m-gram language modeling. 1995 International Conference on Acoustics, Speech, and Signal Processing, 1:181–184 vol.1. [find](https://scholar.google.com/scholar?q=Reinhard+Kneser+and+Hermann+Ney%2E+1995%2E+Improved+backing%2Doff+for+m%2Dgram+language+modeling%2E+1995+International+Conference+on+Acoustics%2C+Speech%2C+and+Signal+Processing%2C+1%3A181%E2%80%93184+vol%2E1%2E)
24. Patricia Kuhl, Feng-Ming Tsao, and Huei-Mei Liu. 2003. Foreign-language experience in infancy: Effects of short-term exposure and social interaction on phonetic learning. Proceedings of the National Academy of Sciences, 100:9096–101. [find](https://scholar.google.com/scholar?q=Patricia+Kuhl%2C+Feng%2DMing+Tsao%2C+and+Huei%2DMei+Liu%2E+2003%2E+Foreign%2Dlanguage+experience+in+infancy%3A+Effects+of+short%2Dterm+exposure+and+social+interaction+on+phonetic+learning%2E+Proceedings+of+the+National+A)
25. Adhiguna Kuncoro, Chris Dyer, John Hale, Dani Yogatama, Stephen Clark, and Phil Blunsom. 2018. LSTMs can learn syntax-sensitive dependencies well, but modeling structure makes them better. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape… [find](https://scholar.google.com/scholar?q=Adhiguna+Kuncoro%2C+Chris+Dyer%2C+John+Hale%2C+Dani+Yogatama%2C+Stephen+Clark%2C+and+Phil+Blunsom%2E+2018%2E+LSTMs+can+learn+syntax%2Dsensitive+dependencies+well%2C+but+modeling+structure+makes+them+better%2E+In+Proceedi)
26. Marta Kutas, Katherine A DeLong, and Nathaniel J Smith. 2011. A look around at what lies ahead: Prediction and predictability in language processing. In Predictions in the brain: Using our past to generate a future, pages 190–207. Oxford University Press. [find](https://scholar.google.com/scholar?q=Marta+Kutas%2C+Katherine+A+DeLong%2C+and+Nathaniel+J+Smith%2E+2011%2E+A+look+around+at+what+lies+ahead%3A+Prediction+and+predictability+in+language+processing%2E+In+Predictions+in+the+brain%3A+Using+our+past+to+gen)
27. Kushal Lakhotia, Eugene Kharitonov, Wei-Ning Hsu, Yossi Adi, Adam Polyak, Benjamin Bolte, Tu-Anh Nguyen, Jade Copet, Alexei Baevski, Abdelrahman Mohamed, and Emmanuel Dupoux. 2021. On generative spoken language modeling from raw audio. Transactions of the Association for Computational Linguistics, 9… [our card](https://md.research.elamur.ai/free/en/papers/lakhotia-2021-generative-spoken-language-modeling-raw/)
28. Howard Lasnik and Jeffrey L Lidz. 2017. The argument from the poverty of the stimulus. The Oxford handbook of universal grammar, pages 221–248. [find](https://scholar.google.com/scholar?q=Howard+Lasnik+and+Jeffrey+L+Lidz%2E+2017%2E+The+argument+from+the+poverty+of+the+stimulus%2E+The+Oxford+handbook+of+universal+grammar%2C+pages+221%E2%80%93248%2E)
29. Julie Anne Legate and Charles D Yang. 2002. Empirical re-assessment of stimulus poverty arguments. The Linguistic Review, 19(1-2):151–162. [find](https://scholar.google.com/scholar?q=Julie+Anne+Legate+and+Charles+D+Yang%2E+2002%2E+Empirical+re%2Dassessment+of+stimulus+poverty+arguments%2E+The+Linguistic+Review%2C+19%281%2D2%29%3A151%E2%80%93162%2E)
30. Michael Lepori, Tal Linzen, and R. Thomas McCoy. 2020. Representations of syntax [MASK] useful: Effects of constituency and dependency structure in recursive LSTMs. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3306–3316, Online. Association for Co… [find](https://scholar.google.com/scholar?q=Michael+Lepori%2C+Tal+Linzen%2C+and+R%2E+Thomas+McCoy%2E+2020%2E+Representations+of+syntax+%5BMASK%5D+useful%3A+Effects+of+constituency+and+dependency+structure+in+recursive+LSTMs%2E+In+Proceedings+of+the+58th+Annual+M)
31. Roger Levy. 2008. Expectation-based syntactic comprehension. Cognition, 106(3):1126–1177. [find](https://scholar.google.com/scholar?q=Roger+Levy%2E+2008%2E+Expectation%2Dbased+syntactic+comprehension%2E+Cognition%2C+106%283%29%3A1126%E2%80%931177%2E)
32. John Lewis and Jeffrey Elman. 2001. Learnability and the statistical structure of language: Poverty of stimulus arguments revisited. Proceedings of the 26th Annual Boston University Conference on Language Development, 1. [find](https://scholar.google.com/scholar?q=John+Lewis+and+Jeffrey+Elman%2E+2001%2E+Learnability+and+the+statistical+structure+of+language%3A+Poverty+of+stimulus+arguments+revisited%2E+Proceedings+of+the+26th+Annual+Boston+University+Conference+on+Lang)
33. Yongjie Lin, Yi Chern Tan, and Robert Frank. 2019. Open sesame: Getting inside BERT’s linguistic knowledge. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 241–253, Florence, Italy. Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/lin-2019-open-sesame-getting-inside-bert/)
34. Tal Linzen. 2020. How can we accelerate progress towards human-like linguistic generalization? In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5210– 5217, Online. Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/linzen-2020-how-can-we-accelerate-progress/)
35. Brian MacWhinney. 2000. The CHILDES project: Tools for analyzing talk. Lawrence Erlbaum Associates. [find](https://scholar.google.com/scholar?q=Brian+MacWhinney%2E+2000%2E+The+CHILDES+project%3A+Tools+for+analyzing+talk%2E+Lawrence+Erlbaum+Associates%2E)
36. R. Thomas McCoy, Robert Frank, and Tal Linzen. 2018. Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks. In Proceedings of the 40th Annual Meeting of the Cognitive Science Society, Madison, WI. [find](https://scholar.google.com/scholar?q=R%2E+Thomas+McCoy%2C+Robert+Frank%2C+and+Tal+Linzen%2E+2018%2E+Revisiting+the+poverty+of+the+stimulus%3A+hierarchical+generalization+without+a+hierarchical+bias+in+recurrent+neural+networks%2E+In+Proceedings+of+the)
37. Jackson Petty and Robert Frank. 2021. Transformers generalize linearly. ArXiv:2109.12036. — [arXiv:2109.12036](https://arxiv.org/abs/2109.12036) [find](https://scholar.google.com/scholar?q=Jackson+Petty+and+Robert+Frank%2E+2021%2E+Transformers+generalize+linearly%2E+ArXiv%3A2109%2E12036%2E+%E2%80%94+%5BarXiv%3A2109%2E12036%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2109%2E12036%29)
38. 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. [our card](https://md.research.elamur.ai/free/en/papers/mccoy-2020-does-syntax-need-grow-trees/)
39. Florencia Reali and Morten H. Christiansen. 2005. Uncovering the richness of the stimulus: Structure dependence and indirect statistical evidence. Cognitive Science, 29(6):1007–1028. [find](https://scholar.google.com/scholar?q=Florencia+Reali+and+Morten+H%2E+Christiansen%2E+2005%2E+Uncovering+the+richness+of+the+stimulus%3A+Structure+dependence+and+indirect+statistical+evidence%2E+Cognitive+Science%2C+29%286%29%3A1007%E2%80%931028%2E)
40. James L. Morgan and Katherine Demuth. 1996. Signal to syntax: Bootstrapping from speech to grammar in early acquisition. Psychology Press. [find](https://scholar.google.com/scholar?q=James+L%2E+Morgan+and+Katherine+Demuth%2E+1996%2E+Signal+to+syntax%3A+Bootstrapping+from+speech+to+grammar+in+early+acquisition%2E+Psychology+Press%2E)
41. Aaron Mueller, Robert Frank, Tal Linzen, Luheng Wang, and Sebastian Schuster. 2022. Coloring the blank slate: Pre-training imparts a hierarchical inductive bias to sequence-to-sequence models. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1352–1368, Dublin, Ireland. A… [find](https://scholar.google.com/scholar?q=Aaron+Mueller%2C+Robert+Frank%2C+Tal+Linzen%2C+Luheng+Wang%2C+and+Sebastian+Schuster%2E+2022%2E+Coloring+the+blank+slate%3A+Pre%2Dtraining+imparts+a+hierarchical+inductive+bias+to+sequence%2Dto%2Dsequence+models%2E+In+Find)
42. Karl Mulligan, Robert Frank, and Tal Linzen. 2021. Structure here, bias there: Hierarchical generalization by jointly learning syntactic transformations. In Proceedings of the Society for Computation in Linguistics 2021, pages 125–135, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Karl+Mulligan%2C+Robert+Frank%2C+and+Tal+Linzen%2E+2021%2E+Structure+here%2C+bias+there%3A+Hierarchical+generalization+by+jointly+learning+syntactic+transformations%2E+In+Proceedings+of+the+Society+for+Computation+)
43. Ludovica Pannitto and Aurélie Herbelot. 2020. Recurrent babbling: Evaluating the acquisition of grammar from limited input data. In Proceedings of the 24th Conference on Computational Natural Language Learning, pages 165–176, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ludovica+Pannitto+and+Aur%C3%A9lie+Herbelot%2E+2020%2E+Recurrent+babbling%3A+Evaluating+the+acquisition+of+grammar+from+limited+input+data%2E+In+Proceedings+of+the+24th+Conference+on+Computational+Natural+Language)
44. Geoffrey K. Pullum and Barbara C. Scholz. 2002. Empirical assessment of stimulus poverty arguments. The Linguistic Review, 18(1-2):9–50. [find](https://scholar.google.com/scholar?q=Geoffrey+K%2E+Pullum+and+Barbara+C%2E+Scholz%2E+2002%2E+Empirical+assessment+of+stimulus+poverty+arguments%2E+The+Linguistic+Review%2C+18%281%2D2%29%3A9%E2%80%9350%2E)
45. Meredith L. Rowe and Adriana Weisleder. 2020. Language development in context. Annual Review of Developmental Psychology, 2(1):201–223. [find](https://scholar.google.com/scholar?q=Meredith+L%2E+Rowe+and+Adriana+Weisleder%2E+2020%2E+Language+development+in+context%2E+Annual+Review+of+Developmental+Psychology%2C+2%281%29%3A201%E2%80%93223%2E)
46. Haoyue Shi, Jiayuan Mao, Kevin Gimpel, and Karen Livescu. 2019. Visually grounded neural syntax acquisition. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1842–1861, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Haoyue+Shi%2C+Jiayuan+Mao%2C+Kevin+Gimpel%2C+and+Karen+Livescu%2E+2019%2E+Visually+grounded+neural+syntax+acquisition%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C)
47. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems, pages 5998–6008. [our card](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/)
48. Alex Warstadt and Samuel R Bowman. 2020. Can neural networks acquire a structural bias from raw linguistic data? Proceedings of the 42nd Annual Conference of the Cognitive Science Society. [find](https://scholar.google.com/scholar?q=Alex+Warstadt+and+Samuel+R+Bowman%2E+2020%2E+Can+neural+networks+acquire+a+structural+bias+from+raw+linguistic+data%3F+Proceedings+of+the+42nd+Annual+Conference+of+the+Cognitive+Science+Society%2E)
49. Alex Warstadt and Samuel R. Bowman. 2022. What artificial neural networks can tell us about human language acquisition. In Shalom Lappin and Jean-Philippe Bernardy, editors, Algebraic Structures in Natural Language. Taylor and Francis. [our card](https://md.research.elamur.ai/free/en/papers/warstadt-2022-artificial-neural-networks-tell-us/)
50. Adam Pauls and Dan Klein. 2012. Large-scale syntactic language modeling with treelets. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 959–968, Jeju Island, Korea. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Adam+Pauls+and+Dan+Klein%2E+2012%2E+Large%2Dscale+syntactic+language+modeling+with+treelets%2E+In+Proceedings+of+the+50th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers)
51. Alex Warstadt, Alicia Parrish, Haokun Liu, Anhad Mohananey, Wei Peng, Sheng-Fu Wang, and Samuel R Bowman. 2020a. BLiMP: The benchmark of linguistic minimal pairs for English. Transactions of the Association for Computational Linguistics, 8:377– 392. [find](https://scholar.google.com/scholar?q=Alex+Warstadt%2C+Alicia+Parrish%2C+Haokun+Liu%2C+Anhad+Mohananey%2C+Wei+Peng%2C+Sheng%2DFu+Wang%2C+and+Samuel+R+Bowman%2E+2020a%2E+BLiMP%3A+The+benchmark+of+linguistic+minimal+pairs+for+English%2E+Transactions+of+the+Assoc)
52. Lisa Pearl. 2021. Poverty of the stimulus without tears. Language Learning and Development, pages 1–40. [find](https://scholar.google.com/scholar?q=Lisa+Pearl%2E+2021%2E+Poverty+of+the+stimulus+without+tears%2E+Language+Learning+and+Development%2C+pages+1%E2%80%9340%2E)
53. Alex Warstadt, Yian Zhang, Xiaocheng Li, Haokun Liu, and Samuel R. Bowman. 2020b. Learning which features matter: RoBERTa acquires a preference for linguistic generalizations (eventually). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 217–23… [find](https://scholar.google.com/scholar?q=Alex+Warstadt%2C+Yian+Zhang%2C+Xiaocheng+Li%2C+Haokun+Liu%2C+and+Samuel+R%2E+Bowman%2E+2020b%2E+Learning+which+features+matter%3A+RoBERTa+acquires+a+preference+for+linguistic+generalizations+%28eventually%29%2E+In+Proceedi)
54. Lisa Pearl and Benjamin Mis. 2016. The role of indirect positive evidence in syntactic acquisition: A look at anaphoric one. Language, 92:1–30. [find](https://scholar.google.com/scholar?q=Lisa+Pearl+and+Benjamin+Mis%2E+2016%2E+The+role+of+indirect+positive+evidence+in+syntactic+acquisition%3A+A+look+at+anaphoric+one%2E+Language%2C+92%3A1%E2%80%9330%2E)
55. Lisa Pearl and Jon Sprouse. 2013a. Computational models of acquisition for islands. In Experimental syntax and island effects, pages 109–131. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Lisa+Pearl+and+Jon+Sprouse%2E+2013a%2E+Computational+models+of+acquisition+for+islands%2E+In+Experimental+syntax+and+island+effects%2C+pages+109%E2%80%93131%2E+Cambridge+University+Press%2E)
56. Lisa Pearl and Jon Sprouse. 2013b. Syntactic islands and learning biases: Combining experimental syntax and computational modeling to investigate the language acquisition problem. Language Acquisition, 20(1):23–68. [find](https://scholar.google.com/scholar?q=Lisa+Pearl+and+Jon+Sprouse%2E+2013b%2E+Syntactic+islands+and+learning+biases%3A+Combining+experimental+syntax+and+computational+modeling+to+investigate+the+language+acquisition+problem%2E+Language+Acquisition)
57. Andrew Perfors, Josh Tenenbaum, and Terry Regier. 2011. The learnability of abstract syntactic principles. Cognition, 118:306–338. [find](https://scholar.google.com/scholar?q=Andrew+Perfors%2C+Josh+Tenenbaum%2C+and+Terry+Regier%2E+2011%2E+The+learnability+of+abstract+syntactic+principles%2E+Cognition%2C+118%3A306%E2%80%93338%2E)
58. Ethan Wilcox, Richard Futrell, and Roger Levy. 2022. Using computational models to test syntactic learnability. Linguistic Inquiry, pages 1–88. [find](https://scholar.google.com/scholar?q=Ethan+Wilcox%2C+Richard+Futrell%2C+and+Roger+Levy%2E+2022%2E+Using+computational+models+to+test+syntactic+learnability%2E+Linguistic+Inquiry%2C+pages+1%E2%80%9388%2E)
59. Ethan Wilcox, Roger Levy, Takashi Morita, and Richard Futrell. 2018. What do RNN language models learn about filler–gap dependencies? In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 211–221, Brussels, Belgium. Association for Computati… [our card](https://md.research.elamur.ai/free/en/papers/wilcox-2018-rnn-language-models-learn-about/)
60. Taha Yasseri, András Kornai, and János Kertész. 2012. A practical approach to language complexity: A Wikipedia case study. PLoS ONE, 7(11):e48386. [find](https://scholar.google.com/scholar?q=Taha+Yasseri%2C+Andr%C3%A1s+Kornai%2C+and+J%C3%A1nos+Kert%C3%A9sz%2E+2012%2E+A+practical+approach+to+language+complexity%3A+A+Wikipedia+case+study%2E+PLoS+ONE%2C+7%2811%29%3Ae48386%2E)