SEMANTIC NETWORK METHODS TO DISAMBIGUATE NATURAL LANGUAGE MEANING

• US 20100030724A1
• Filed: 10/10/2009
• Published: 02/04/2010
• Est. Priority Date: 05/28/1998
• Status: Active Grant

• Current Assignee: DataCloud Technologies, LLC (IP Investments Group LLC)
• Original Assignee: QPS Tech LLC (Intellectual Ventures LLC)
• Inventors: Au, Lawrence
• Granted Patent: US 8,135,660 B2
• Time in Patent Office: Days
• 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 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.

Claims

1. A computer-readable storage medium having stored thereon instructions that, when executed, cause a machine to:

receive a natural language input comprising a plurality of symbols;

store a plurality of input nodes in a semantic network, wherein one or more of the input nodes have polysemy, wherein a plurality of candidate meanings for at least one of the input nodes having polysemy are stored respectively as a plurality of candidate nodes in the semantic network, and wherein the semantic network includes a stored natural language context, the stored natural language context including a plurality of context nodes;

identify a plurality of semantic links, 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;

compute 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 at least one of the input nodes having polysemy; and

select at least one of the plurality of candidate nodes for 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 corresponding input node.

2. The computer-readable storage medium of claim 1, wherein comparing two or more of the contextual distances to determine a contextual distance comprises:

determining a minimum average link distance between at least one of the plurality of candidate nodes and at least one of the plurality of context nodes.

3. The computer-readable storage medium of claim 1, wherein the semantic network includes a plurality of semantic nodes, and wherein at least one of the selected candidate nodes inherits from a common semantic network node, the common semantic network node being selected from the plurality of semantic nodes.

4. The computer-readable storage medium of claim 1, wherein no semantic links are identified as traversing from at least one of the plurality of candidate nodes to at least one of the plurality of context nodes for at least one of the plurality of semantic link types.

5. The computer-readable storage medium of claim 4, wherein, in response to no semantic links being identified as traversing from at least one of the plurality of candidate nodes to at least one of the plurality of context nodes, estimating a distance from at least one of the plurality of candidate nodes to at least one of the plurality of context nodes.

6. The computer-readable storage medium of claim 4, wherein at least one of the plurality of semantic links corresponds to at least one of a plurality of semantic link types.

7. The computer-readable storage medium of claim 1, wherein the plurality of input candidate nodes are received at the machine via voice recognition capability of the machine.

8. The computer-readable storage medium of claim 1, wherein the machine is a household appliance.

9. The computer-readable storage medium of claim 8, wherein the household appliance is a microwave oven.

10. The computer-readable storage medium of claim 1, wherein the machine is a hand-held device.

11. The computer-readable storage medium of claim 1, wherein the machine is a wireless communication device.

12. The computer-readable storage medium of claim 1, wherein the machine is configured to perform one or more voice synthesis functions.

13. A computing device comprising:

a natural language processor comprising;

a natural language user interface adapted to receive a natural language input, wherein the natural language input is at least one of visual input or audio input;

a pre-processor communicatively coupled to the natural language user interface and adapted to receive the natural language input and convert the natural language input to a sequence of symbols having an associated sequence order;

a memory communicatively coupled to the pre-processor and storing;

a semantic network comprising;

a set of semantic network nodes representative of the sequence of symbols, wherein the set of semantic network nodes are stored as successive input sequences having the associated sequence order;

a plurality of semantic network links; and

a set of meaning nodes representative of the natural language meaning; and

a natural language processing unit communicatively coupled to the pre-processor for receiving the sequence of symbols, the natural language processing unit comprising a natural language conversion device adapted to;

determine a natural language meaning of the sequence of symbols; and

retrieve the natural language meaning from the semantic network stored in the memory.

14. The computing device of claim 13, wherein the natural language meaning is recorded redundantly by a plurality of paths over a plurality of semantic links connecting one or more semantic network nodes.

15. The computing device of claim 13, wherein the computing device is a household appliance.

16. The computing device of claim 13, wherein the computing device is wireless communication apparatus.

17. A computer-readable storage medium having stored thereon instructions that, when executed, cause a machine to:

receive an input sequence of symbols, the input sequence of symbols being in a sequence order and having a natural language meaning determined from a context node filter and a contextual distance function;

store the input sequence of symbols as a new set of semantic network nodes in a semantic network, the new set of semantic network nodes being stored as successive input sequences having the sequence order, the semantic network having a plurality of semantic network links and being stored in a memory of the machine;

store the natural language meaning as a set of meaning nodes in the semantic network; and

retrieve the natural language meaning for the input sequence of symbols from the semantic network.

18. The computer-readable storage medium of claim 17, wherein the contextual distance function is at least one of a minimum average distance, a maximum average distance, a minimum distance or a maximum distance.

19. The computer-readable storage medium of claim 17, wherein the context node filter is configured to accept nodes that are nouns or verbs.

20. The computer-readable storage medium of claim 17, wherein the context node filter is configured to accept nodes that are identified in conversation.