Fig. 4: Example of calculating concept embeddings from an abstract. | Nature Machine Intelligence

Fig. 4: Example of calculating concept embeddings from an abstract.

From: Predicting new research directions in materials science using large language models and concept graphs

Fig. 4: Example of calculating concept embeddings from an abstract.

Embeddings of verbatim concepts (‘mechanical stress’) are calculated by averaging all local MatSciBert embeddings of the corresponding tokens (4,487 and 1,893). Embeddings of non-verbatim concepts (‘nitride film’ is only present in the abstract in its unnormalized form ‘nitride films’) are calculated as the average of all token embeddings. x represents the embedding vectors of the tokens.

Back to article page