International Business Machines Corporation
Methods and systems for generating descriptions utilizing extracted entity descriptors

Abstract:

Embodiments for generating descriptions of entities are provided. A plurality of references to an entity within a corpus are identified. The corpus includes a plurality of documents. Descriptors for the entity are extracted from portions of the plurality of documents associated with the plurality of references to the entity. A score for each of the descriptors is calculated based on at least one of a location of the reference associated with the descriptor within the respective document and a location of the descriptor within the respective document. A description of the entity is generated utilizing at least some of the descriptors based on said calculated scores.