Recent work uses a language model to gain insight into how the human brain understands the combined meaning of words in a sentence, and uncovers parts of the brain that contribute to this understanding.
This is a preview of subscription content, log in via an institution to check access.
References
Toneva, M., Mitchell, T. M. & Wehbe, L. Nat. Comput. Sci. https://doi.org/10.1038/s43588-022-00354-6 (2022).
Bommasani, R. et al. Preprint at https://arxiv.org/abs/2108.07258 (2021).
Peters, M. et al. Deep contextualized word representations. In Proc. 2018 Conference of the North American Chapter of the Association for Computational Linguistics 2227–2237 (Association for Computational Linguistics, 2018).
Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. In Proc. 2019 Conference of the North American Chapter of the Association for Computational Linguistics 4171–4186 (Association for Computational Linguistics, 2019).
Radford, A. et al. OpenAI blog 1, 9 (2019).
Vulić, I., Ponti, E. M., Litschko. R., Glavaš, G. & Korhonen, A. Probing pretrained language models for lexical semantics. In Proc. 2020 Conference on Empirical Methods in Natural Language Processing 7222–7240 (Association for Computational Linguistics, 2020).
Linzen, T., Dupoux, E. & Goldberg, Y. Trans. Assoc. Comput. Linguist. 4, 521–535 (2016).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The author declares no competing interests.
Rights and permissions
About this article
Cite this article
Erk, K. Understanding the combined meaning of words. Nat Comput Sci 2, 701–702 (2022). https://doi.org/10.1038/s43588-022-00338-6
Published:
Issue Date:
DOI: https://doi.org/10.1038/s43588-022-00338-6
- Springer Nature America, Inc.