Skip to main content
. 2022 Apr 8;3(5):100483. doi: 10.1016/j.patter.2022.100483

Figure 4.

Figure 4

t-distributed stochastic neighbor embedding (t-SNE) projection in 2 dimensions of title and abstract BioBERT autoencoder embeddings

(A and B) Labeled by the presence (orange) or absence (blue) of a guideline or policy (A) or patent (B) inclusion. Note the discernible data structure that enables accurate prediction of inclusion but is too complex to be reduced to any small set of characteristic features.