公开(公告)号：GB2596729A

公开(公告)日：2022-01-05

申请号：GB202114479

申请日：2020-05-15

Applicant: IBM

Inventor： CRAIG TRIM ,  MARY RUDDEN ,  MAURO MARZORATI ,  JEREMY FOX

IPC: G06N5/02

Abstract: Systems and methods for automated resolution of over-specification and under-specification in a knowledge graph are disclosed. In embodiments, a method includes: determining, by a computing device, that a size of an object cluster of a knowledge graph meets a threshold value indicating under-specification of a knowledge base of the knowledge graph; determining, by the computing device, sub-classes for objects of the knowledge graph; re-initializing, by the computing device, the knowledge graph based on the sub-classes to generate a refined knowledge graph, wherein the size of the object cluster is reduced in the refined knowledge graph; and generating, by the computing device, an output based on information determined from the refined knowledge graph.

公开(公告)号：GB2599334A

公开(公告)日：2022-03-30

申请号：GB202200630

申请日：2020-06-12

Applicant: IBM

Inventor： CRAIG TRIM ,  MARY RUDDEN ,  AARON BAUGHMAN ,  STEFAN VAN DER STOCKT ,  BERNARD FREUND ,  AUGUSTINA RAGWITZ

IPC: G06N5/02 ,  G06N3/04 ,  G06N20/00

Abstract: A transitive closure data structure is constructed for a pair of features represented in a vector space corresponding to an input dataset. The data structure includes a set of entries corresponding to a set of all possible paths between a first feature in the pair and a second feature in the pair in a graph of the vector space. The data structure is reduced by removing a subset of the set of entries such that only a single entry corresponding to a single path remains in the transitive closure data structure. A feature cross is formed from a cluster of features remaining in a reduced ontology graph resulting from the reducing the transitive closure data structure. A layer is configured in a neural network to represent the feature cross, which causes the neural network to produce a prediction that is within a defined accuracy relative to the dataset.