Tag: machine-learning

Semantic projection recovers rich human knowledge of multiple object features from word embeddings (Grand et. al. 2022) is a very cool paper. It shows that simple word embeddings don’t just stand in linear conceptual relations to each other (i.e. v(king) - v(man) + v(woman) = v(queen)), but that there are interpretable subspaces within the embedding… Continue reading A Semantic Subspace in Philosophy →