Transformer methods are revolutionizing how computers process human language. Exploiting the structural similarity between human lives, seen as sequences of events, and natural-language sentences, a transformer method — dubbed life2vec — has been used to create rich vector representations of human lives, from which accurate predictions can be made.
This is a preview of subscription content, log in via an institution to check access.
References
Vaswani, A. et al. Attention is all you need. In Advances in Neural Information Processing Systems 30 (eds Guyon, I. et al.) (Curran Associates, Inc., 2017). This paper introduces the idea of transformers.
Tunstall, L., von Werra, L. & Wolf, T. Natural Language Processing with Transformers (O’Reilly Media, 2022). This book includes a gentle introduction to word embeddings.
Kim, B. et al. Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). Proc. Mach. Learn. Res. 80, 2668–2677 (2018). This paper introduces the idea of topic concept activation vectors.
Wang, Y., Huang, H., Rudin, C. & Shaposhnik, Y. Understanding how dimension reduction tools work: an empirical approach to deciphering t-SNE, UMAP, TriMAP and PaCMAP for data visualization. J. Mach. Learn. Res. 22, 1–73 (2021). This paper presents the method we have used for generating visualizations of the embedding space.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Savcisens, G. et al. Using sequences of life-events to predict human lives. Nat. Comput. Sci. https://doi.org/10.1038/s43588-023-00573-5 (2023).
Rights and permissions
About this article
Cite this article
A transformer method that predicts human lives from sequences of life events. Nat Comput Sci 4, 7–8 (2024). https://doi.org/10.1038/s43588-023-00586-0
Published:
Issue Date:
DOI: https://doi.org/10.1038/s43588-023-00586-0
- Springer Nature America, Inc.