US 11,755,843 B2
Filtering spurious knowledge graph relationships between labeled entities
Nandana Mihindukulasooriya, Cambridge, MA (US); Robert G. Farrell, Cornwall, NY (US); Nicolas Rodolfo Fauceglia, New York, NY (US); and Alfio Massimiliano Gliozzo, Brooklyn, NY (US)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on May 18, 2021, as Appl. No. 17/323,584.
Application 17/323,584 is a continuation of application No. 16/600,774, filed on Oct. 14, 2019, granted, now 11,080,491.
Prior Publication US 2021/0279422 A1, Sep. 9, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/30 (2020.01); G06F 16/335 (2019.01); G06F 16/901 (2019.01); G06F 40/211 (2020.01); G06F 40/247 (2020.01); G06F 40/268 (2020.01); G06F 40/284 (2020.01); G06F 40/295 (2020.01)
CPC G06F 40/30 (2020.01) [G06F 16/335 (2019.01); G06F 16/9024 (2019.01); G06F 40/211 (2020.01); G06F 40/247 (2020.01); G06F 40/268 (2020.01); G06F 40/284 (2020.01); G06F 40/295 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a memory that stores computer-executable components; and
at least a processor, operably coupled to the memory, that executes the computer-executable components stored in the memory, wherein the computer-executable components comprise:
a context component that:
generates a context-based embedding of one or more first terms in a document collection; wherein the context component has a plurality of different modes, wherein respective ones of the plurality of different modes are trained to predict different types of relations and wherein a mode of the plurality of different modes is selected based on a relationship retrieved from a knowledge graph; and
determines that at least two of the one or more first terms that have vector representations that have a similarity value that meets a defined criterion have a hypernymy relation between them, and determines that at least two of the one or more first terms that have vector representations that fail to have a similarity value that meets the defined criterion do not have a hypernymy relation between them, wherein the vector representations are compared to determine whether the hypernymy relation from the knowledge graph for the at least two of the one or more first terms is spurious.