Word Acquisition in Neural Language Models
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
We investigate how neural language models acquire individual words during training, extracting learning curves and ages of acquisition for over 600 words on the MacArthur-Bates Communicative Development Inventory (Fenson et al., 2007). Drawing on studies of word acquisition in children, we evaluate multiple predictors for words’ ages of acquisition in LSTMs, BERT, and GPT-2. We find that the effects of concreteness, word length, and lexical class are pointedly different in children and language models, reinforcing the importance of interaction and sensorimotor experience in child language acquisition. Language models rely far more on word frequency than children, but, like children, they exhibit slower learning of words in longer utterances. Interestingly, models follow consistent patterns during training for both unidirectional and bidirectional models, and for both LSTM and Transformer architectures. Models predict based on unigram token frequencies early in training, before transitioning loosely to bigram probabilities, eventually converging on more nuanced predictions. These results shed light on the role of distributional learning mechanisms in children, while also providing insights for more human-like language acquisition in language models.
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. (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
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
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
Zhu, Y., Kiros, R., Zemel, R., Salakhutdinov, R., Urtasun, R., Torralba, A., & Fidler, S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.11 · Cited by 2,264
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Lu, J., Batra, D., Parikh, D., & Lee, S. (2019) · arXiv · doi:10.48550/arxiv.1908.02265 · Cited by 2,109
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 · cited 2×
“Recently, there has been substantial research evaluating language models using psycholinguistic approaches, reflecting a broader goal of interpreting language models (BERTology; Rogers et al., 2020).”
BackgroundClimbing towards NLU: On Meaning, Form, and Understanding in the Age of Data
Bender, E. M., & Koller, A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.463 · Cited by 1,082
Statistical learning and language acquisition
Romberg, A. R., & Saffran, J. R. (2010) · WIREs Cognitive Science · doi:10.1002/wcs.78 · Cited by 517
What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models
Ettinger, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00298 · Cited by 511
Mapping the Early Language Environment Using All-Day Recordings and Automated Analysis
Gilkerson, J., Richards, J. A., Warren, S. F., Montgomery, J. K., Greenwood, C. R., Kimbrough Oller, D., Hansen, J. H. L., & Paul, T. D. (2017) · American Journal of Speech-Language Pathology · doi:10.1044/2016_ajslp-15-0169 · Cited by 472
Cited by
Language Model Behavior: A Comprehensive Survey
Chang, T. A., & Bergen, B. K. (2024) · Computational Linguistics · doi:10.1162/coli_a_00492 · Cited by 105
Self-citationMemorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
Tirumala, K., Markosyan, A., Zettlemoyer, L., & Aghajanyan, A. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2773 · Cited by 67
Hosseini, E. A., Schrimpf, M., Zhang, Y., Bowman, S., Zaslavsky, N., & Fedorenko, E. (2024) · Neurobiology of Language · doi:10.1162/nol_a_00137 · Cited by 63
“…is that their training data size (often, billions of words) far surpasses the amount of language exposure in humans during their learning phase (Chang & Bergen, 2021; Dupoux, 2018; Frank, 2023; Linzen & Leonard, 2018; van Schijndel et al., 2019; see Warstadt & Bowman, 2022, for discussion).”
BackgroundDistributional Semantics: Meaning Through Culture and Interaction
Contreras Kallens, P., & Christiansen, M. H. (2025) · Topics in Cognitive Science · doi:10.1111/tops.12771 · Cited by 17
Portelance, E., Duan, Y., Frank, M. C., & Lupyan, G. (2023) · Cognitive Science · doi:10.1111/cogs.13334 · Cited by 15
Metadata
- Authors
- Chang, T. A., & Bergen, B. K.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2022
- Volume
- 10
- Pages
- 1-16
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W3202180397
- Cited by
- 26
- References
- 13
- FWCI
- 8.50
- Type
- journal article
- Language
- en
- Open access
- diamond
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: Word Acquisition in Neural Language Models. https://app.cochat.ai/papers/10.1162/tacl_a_00444
- The paper
- Chang, T. A., & Bergen, B. K. (2022). Word Acquisition in Neural Language Models. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00444
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.