Semantic network methods to disambiguate natural language meaning

1. A non-transitory computer-readable medium having instructions stored thereon, the instructions comprising:

instructions to receive an input sequence of symbols having a meaning determined from a context node filter and a contextual distance function;

instructions to store the input sequence of symbols in a semantic network having a plurality of nodes, wherein the input sequence of symbols is stored as pairs of subject and predicate nodes linked by verb nodes, wherein the stored pairs of subject and predicate nodes are linked by the verb nodes inherited from a previously-stored set of a plurality of meaning nodes;

instructions to scan the semantic network for at least one common meaning node in the plurality of meaning nodes corresponding to the stored pairs of subject and predicate nodes linked by the verb nodes;

instructions to create in the semantic network is-a links between at least one pair of subject and predicate nodes of the same input sequence of symbols;

instructions to delete from the semantic network, verb nodes and duplicate pairs of subject and predicate nodes in other stored input sequences of symbols from the at least one pair of subject and predicate nodes of the same input sequence of symbols; and

instructions to retrieve the natural language meaning for the received input sequence of symbols.

2. The non-transitory computer-readable medium of claim 1 , wherein the is-a links are dictionary links from parse phrase trees containing ‘is’ and ‘a’ phrasing.

3. The non-transitory computer-readable medium of claim 1 , wherein the contextual distance function is at least one of a minimum distance or a maximum distance.

4. The non-transitory computer-readable medium of claim 1 , wherein the context node filter is configured to operate with a context type filter.

5. The non-transitory computer-readable medium of claim 4 , wherein the context type filter is configured to output a context type associated with determining a contextual distance.

6. The non-transitory computer-readable medium of claim 1 , wherein the context node filter is configured to operate with a traversal type filter, wherein the traversal type filter is configured to accept nodes that are traversal types.

7. The non-transitory computer-readable medium of claim 1 , wherein the context node filter is configured to operate with a category set filter, wherein the category set filter is configured to accept nodes that inherit from adjectives or adverbs.

8. A computing device, comprising:

a natural language user interface configured to receive a natural language input, wherein the natural language input is visual input or audio input;

a pre-processor configured to:

map the natural language input to at least one of a plurality of input nodes or map the natural language input to a new input node, the new input node being created by the pre-processor and included in the plurality of input nodes;

a memory storing:

a semantic network, wherein the semantic network comprises:

the plurality of input nodes, wherein at least one of the plurality of input nodes has polysemy;

a plurality of candidate nodes associated with a plurality of candidate meanings for the at least one of the input nodes having polysemy;

a natural language context including a plurality of context nodes; and

a plurality of semantic links, wherein at least one of the plurality of semantic links traverses from at least one of the plurality of candidate nodes to at least one of the plurality of context nodes; and

a natural language processing unit communicatively coupled to the memory and configured to:

compute a plurality of contextual distances for the plurality of semantic links;

compare two or more of the plurality of contextual distances to determine a contextual distance for the at least one of the input nodes having polysemy based at least on a contextual distance function; and

select at least one of the plurality of candidate nodes for the at least one of the input nodes having polysemy, wherein the selected at least one of the plurality of candidate nodes has an associated contextual distance approximating the determined contextual distance for the corresponding input node.

9. The computing device of claim 8 , wherein the visual input is an image.

10. The computing device of claim 8 , wherein the computing device is a household appliance.

11. The computing device of claim 8 , wherein the computing device is a hand-held apparatus.

12. The computing device of claim 8 , wherein the computing device is a wireless communication apparatus.

13. A non-transitory computer-readable medium having instructions stored thereon, the instructions comprising:

instructions to identify a set of inheritance sibling nodes;

instructions to compute an average abstractness for a plurality of inheritance sibling nodes in the set of inheritance sibling nodes;

instructions to compute an abstractness deviation from the average abstractness, wherein the computing is for the plurality of the inheritance sibling nodes;

instructions to sum the abstractness deviations for the plurality of inheritance sibling nodes;

instructions to compare the summed abstractness deviation of the plurality of inheritance sibling nodes to a summed abstractness deviation of an alternative topology for an alternative set of inheritance sibling nodes; and

instructions to revise semantic network inheritance link topology by:

in response to the plurality of inheritance sibling nodes having a summed abstractness deviation that is less than the summed abstractness deviation of the alternative topology, selecting a topology associated with the plurality of inheritance sibling nodes; or

in response to the plurality of inheritance sibling nodes having a summed abstractness deviation that is not less than the summed abstractness deviation of the alternative topology, selecting the alternative topology.

14. A method, comprising:

identifying, by a computing device, a set of inheritance sibling nodes;

computing an average abstractness for a plurality of inheritance sibling nodes in the set of inheritance sibling nodes;

computing an abstractness deviation from the average abstractness, wherein the computing is for the plurality of the inheritance sibling nodes;

summing the abstractness deviations for the plurality of inheritance sibling nodes;

comparing the summed abstractness deviation of the plurality of inheritance sibling nodes to a summed abstractness deviation of an alternative topology for an alternative set of inheritance sibling nodes; and

revising semantic network inheritance link topology by:

in response to the plurality of inheritance sibling nodes having a summed abstractness deviation that is less than the summed abstractness deviation of the alternative topology, selecting a topology associated with the plurality of inheritance sibling nodes; or

in response to the plurality of inheritance sibling nodes having a summed abstractness deviation that is not less than the summed abstractness deviation of the alternative topology, selecting the alternative topology.