Sign In

henry copeland:

Unsupervised word embeddings capture latent knowledge from materials science literature | Nature

Furthermore, we demonstrate that an unsupervised method can recommend materials for functional applications several years before their discovery. This suggests that latent knowledge regarding future discoveries is to a large extent embedded in past publications. Our findings highlight the possibility of extracting knowledge and relationships from the massive body of scientific literature in a collective manner, and point towards a generalized approach to the mining of scientific literature.
- www.nature.com
networks AI language science
FAQ | Blog | DMCA
© 2025 Pressflex LLC