US 12,001,794 B2
Zero-shot entity linking based on symbolic information
Dinesh Khandelwal, Indore (IN); G P Shrivatsa Bhargav, Bengaluru (IN); Saswati Dana, Bangalore (IN); Dinesh Garg, Beawar (IN); Pavan Kapanipathi Bangalore, Westchester, NY (US); Salim Roukos, Redondo Beach, CA (US); Alexander Gray, Yonkers, NY (US); and L. Venkata Subramaniam, Gurgaon (IN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jan. 14, 2022, as Appl. No. 17/575,951.
Prior Publication US 2023/0229859 A1, Jul. 20, 2023
Int. Cl. G06F 40/279 (2020.01); G06N 5/02 (2023.01)
CPC G06F 40/279 (2020.01) [G06N 5/027 (2013.01)] 20 Claims
OG exemplary drawing
 
20. A system comprising:
a memory configured to store program instructions;
a processor operatively coupled to the memory to execute the program instructions to:
obtain a knowledge graph comprising a set of entities and a training dataset comprising text samples for at least a subset of the entities in the knowledge graph;
train a machine learning model to map an entity mention substring of a given sample of text to one corresponding entity in the set of entities, wherein the machine learning model is trained using a multi-task machine learning framework using symbolic information extracted from the knowledge graph; and
map an entity mention substring of a new sample of text to one of the entities in the set using the trained machine learning model.