US 12,437,105 B2
Data obscuring for natural language text
Benjamin Weggenmann, Karlsruhe (DE); and Valentin Rublack, Cologne (DE)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Nov. 11, 2022, as Appl. No. 17/985,217.
Prior Publication US 2024/0160772 A1, May 16, 2024
Int. Cl. G06F 21/62 (2013.01); G06F 40/284 (2020.01)
CPC G06F 21/6245 (2013.01) [G06F 40/284 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer system for obscuring natural language data, the system comprising:
at least one hardware processor programmed to perform operations comprising:
accessing natural language data, the natural language data comprising a first plurality of sequenced tokens;
applying an encoder model to the first plurality of sequenced tokens to generate a latent space representation of the first plurality of sequenced tokens, the latent space representation comprising a first content latent vector describing a content of the natural language data and a first author latent vector describing an author of the natural language data;
modifying the first author latent vector to generate an obscured author latent vector; and
applying a decoder model to the first content latent vector and the obscured author latent vector to generate obscured natural language data, the obscured natural language data comprising a second plurality of sequenced tokens.