Semantic network methods to disambiguate natural language meaning
First Claim
Patent Images
1. A non-transitory computer-readable medium comprising computer executable instructions that, in response to execution, cause a machine to perform comprising:
- receiving a natural language input comprising a plurality of symbols;
storing the plurality of symbols as a plurality of input nodes in a semantic network, wherein at least one of the input nodes has polysemy, wherein a plurality of candidate meanings for the at least one of the input nodes are stored respectively as a plurality of candidate nodes in the semantic network, and wherein the semantic network includes a stored natural language context comprising a plurality of context nodes;
identifying a plurality of semantic links between nodes of the semantic network, wherein at least one of the plurality of semantic links traverses from one of the plurality of candidate nodes to one of the plurality of context nodes;
computing a contextual distance for two or more of the plurality of semantic links;
comparing two or more of the contextual distances to determine a contextual distance for the at least one of the input nodes; and
select at least one of the plurality of candidate nodes for the at least one of the input nodes, wherein the at least one selected candidate node has an associated contextual distance approximating the contextual distance for the at least one of the input nodes.
4 Assignments
0 Petitions
Accused Products
Abstract
A computer implemented data processor system automatically disambiguates a contextual meaning of natural language symbols to enable precise meanings to be stored for later retrieval from a natural language database, so that natural language database design is automatic, to enable flexible and efficient natural language interfaces to computers, household appliances and hand-held devices.
105 Citations
20 Claims
-
1. A non-transitory computer-readable medium comprising computer executable instructions that, in response to execution, cause a machine to perform comprising:
-
receiving a natural language input comprising a plurality of symbols; storing the plurality of symbols as a plurality of input nodes in a semantic network, wherein at least one of the input nodes has polysemy, wherein a plurality of candidate meanings for the at least one of the input nodes are stored respectively as a plurality of candidate nodes in the semantic network, and wherein the semantic network includes a stored natural language context comprising a plurality of context nodes; identifying a plurality of semantic links between nodes of the semantic network, wherein at least one of the plurality of semantic links traverses from one of the plurality of candidate nodes to one of the plurality of context nodes; computing a contextual distance for two or more of the plurality of semantic links; comparing two or more of the contextual distances to determine a contextual distance for the at least one of the input nodes; and select at least one of the plurality of candidate nodes for the at least one of the input nodes, wherein the at least one selected candidate node has an associated contextual distance approximating the contextual distance for the at least one of the input nodes. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A computing device, comprising:
-
a natural language user interface configured to receive a natural language input, a natural language processor configured to; store the natural language input as a plurality of input nodes in a semantic network, wherein at least one of the input nodes has polysemy, wherein a plurality of candidate meanings for the at least one of the input nodes are stored respectively as a plurality of candidate nodes in the semantic network, and wherein the semantic network includes a stored natural language context comprising a plurality of context nodes; identify a plurality of semantic links between nodes of the semantic network, wherein at least one of the plurality of semantic links traverses from one of the plurality of candidate nodes to one of the plurality of context nodes; computer a contextual distance for two or more of the plurality of semantic links; compare two or more of the contextual distances to determine a contextual distance for the at least one of the input nodes; and select at least one of the plurality of candidate nodes for the at least one of the input nodes having polysemy, wherein the at least one selected candidate node has an associated contextual distance approximating the contextual distance for the at least one of the input nodes. - View Dependent Claims (14, 15, 16)
-
-
17. A system, comprising:
-
means for receiving a natural language input; means for storing the natural language input as a plurality of input nodes in a semantic network, wherein at least one of the input nodes has polysemy, wherein a plurality of candidate meanings for the at least one of the input nodes are stored respectively as a plurality of candidate nodes in the semantic network, and wherein the semantic network includes a stored natural language context comprising a plurality of context nodes; means for identifying a plurality of semantic links between nodes of the semantic network, wherein at least one of the plurality of semantic links traverses from one of the plurality of candidate nodes to one of the plurality of context nodes; means for computing a contextual distance for two or more of the plurality of semantic links; means for comparing two or more of the contextual distances to determine a contextual distance for the at least one of the input nodes; and means for selecting at least one of the plurality of candidate nodes for the at least one of the input nodes having polysemy, wherein the at least one selected candidate node has an associated contextual distance approximating the contextual distance for the at least one of the input nodes. - View Dependent Claims (18, 19, 20)
-
Specification