Systems and methods to increase efficiency in semantic networks to disambiguate natural language meaning

• US 8,204,844 B2
• Filed: 10/10/2009
• Issued: 06/19/2012
• Est. Priority Date: 05/28/1998
• Status: Expired due to Fees

• Current Assignee: DataCloud Technologies, LLC (IP Investments Group LLC)
• Original Assignee: QPS Tech LLC (Intellectual Ventures LLC)
• Inventors: Au, Lawrence
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): Tran, Mai T
• Application Number:
  US12/577,159
• Publication Number:
  US 20100030723A1
• Time in Patent Office: 983 Days
• Field of Search: 706/55, 707/999.01
• US Class Current: 706/55
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 40/237 Lexical tools
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

A computer implemented data processor system shifts a semantic network topology to increase efficiency in disambiguating a contextual meaning of natural language symbols.

Claims

1. A system, comprising:

a processor configured to facilitate execution of one or more computer-executable components, received by the system or stored in memory of the system, that at least;

receive a natural language query;

identify one or more meanings for a data set by removing syntactic ambiguities from the data set using one or more measurements associated with semantic distance to traverse the data set and a plurality of semantic network nodes included in a semantic network dictionary having a topology;

determine a semantic efficiency measure for the semantic network dictionary based upon at least one measure of inheritor node population of the plurality of semantic network nodes and at least one measure of abstractness of the plurality of semantic network nodes; and

rearrange the topology of the plurality of semantic network nodes to increase the semantic efficiency measure in response to detection of an inefficiency in the topology.

2. The system of claim 1, wherein the at least one measure of inheritor node population comprises at least one of a direct inheritor population, a total inheritor population, a direct inheritor deviation, a total inheritor deviation, or an average inheritor deviation.

3. The system of claim 1, wherein the at least one measure of abstractness comprises at least one of a mean inheritor abstractness, an abstract deviation, a total abstract deviation, or an average abstract deviation.

4. The system of claim 1, wherein the one or more computer-executable components further generate a semantically-relevant response to the natural language query, the semantically-relevant response corresponding to at least one of the one or more meanings.

5. The system of claim 4, wherein the one or more computer-executable components further output the semantically-relevant response to a portable device.

6. A method, comprising:

receiving, at a computing device, a natural language query;

traversing a semantic network dictionary using at least one distance measurement, the semantic network dictionary comprising a plurality of semantic network nodes having a topology;

receiving or determining one or more meanings corresponding to at least one of the plurality of semantic network nodes;

determining a semantic efficiency measure for the semantic network dictionary based upon at least one measure of inheritor node population of the plurality of semantic network nodes and at least one measure of abstractness of the plurality of semantic network nodes; and

rearranging the topology of the plurality of semantic network nodes to increase the semantic efficiency measure in response to detecting an inefficiency in the topology.

7. The method of claim 6, further comprising associating at least one of the plurality of semantic network nodes with a stored natural language context.

8. The method of claim 6, wherein the traversing comprises traversing the semantic network dictionary having at least one of the plurality of semantic network nodes inheriting from at least one other of the plurality of semantic network nodes.

9. The method of claim 6, wherein the traversing comprises traversing the semantic network dictionary having at least one link connecting two or more of the plurality of semantic network nodes.

10. The method of claim 6, wherein the traversing comprises traversing the semantic network dictionary using at least one of a minimum average distance or a maximum average distance.

11. The method of claim 6, further comprising:

generating a semantically-relevant response to the natural language query, the semantically-relevant response corresponding to at least one of the one or more meanings.

12. The method of claim 11, further comprising outputting the semantically-relevant response to a voice synthesizer.

13. The method of claim 11, further comprising outputting the semantically-relevant response to a mobile display device.

14. A non-transitory computer readable medium comprising computer executable instructions that, in response to execution, cause at least one device to perform operations, comprising:

receiving a natural language query;

traversing a semantic network dictionary using at least one semantic distance measurement, the semantic network dictionary comprising a plurality of semantic network nodes having a topology;

receiving or determining one or more meanings corresponding to at least one of the plurality of semantic network nodes;

determining a semantic efficiency measure for the semantic network dictionary based upon at least one measure of inheritor node population of the plurality of semantic network nodes and at least one measure of abstractness of the plurality of semantic network nodes; and

rearranging the topology of the plurality of semantic network nodes to increase the semantic efficiency measure in response to detecting an inefficiency in the topology.

15. The non-transitory computer readable medium of claim 14, wherein the traversing comprises traversing the semantic network dictionary having at least one of the plurality of semantic network nodes inheriting from at least one other of the plurality of semantic network nodes.

16. The non-transitory computer readable medium of claim 14, the operations further comprising associating at least one of the plurality of semantic network nodes with a stored natural language context.

17. The non-transitory computer readable medium of claim 14, wherein the traversing comprises traversing the semantic network dictionary having at least one link connecting two or more of the plurality of semantic network nodes.

18. The non-transitory computer readable medium of claim 14, wherein the traversing comprises traversing the semantic network dictionary using at least one of a minimum average distance or a maximum average distance.

19. The non-transitory computer readable medium of claim 14, further comprising:

generating a semantically-relevant response to the natural language query, the semantically-relevant response corresponding to at least one of the one or more meanings.

20. The non-transitory computer readable medium of claim 19, further comprising outputting the semantically-relevant response to a voice synthesizer.

21. The non-transitory computer readable medium of claim 19, further comprising outputting the semantically-relevant response to a display device.

22. A system, comprising:

means for receiving a natural language query;

means for identifying one or more meanings for a data set by removing syntactic ambiguities from the data set using one or more measurements associated with semantic distance to traverse the data set and a plurality of semantic network nodes having a topology;

means for determining a semantic efficiency measure for the topology based upon at least one measure of inheritor node population of the plurality of semantic network nodes and at least one measure of abstractness of the plurality of semantic network nodes; and

means for rearranging the topology of the plurality of semantic network nodes to increase the semantic efficiency measure in response to detecting an inefficiency in the topology.

23. The system of claim 22, further comprising means for generating a semantically-relevant response to the natural language query, the semantically-relevant response corresponding to at least one meaning of the one or more meanings.

24. The system of claim 23, further comprising means for outputting the semantically-relevant response to a voice synthesizer.

25. The system of claim 23, further comprising means for outputting the semantically-relevant response to a display device.