Techniques for graph based natural language processing

1. A computer-implemented method, comprising:

receiving a network query at a network system, the network query to include a natural language user request from a device and a request to match the natural language user request against an object graph;

matching the natural language user request to one or more objects in the object graph, the object graph comprising token mappings for objects within the object graph, the token mappings based on data extracted from a plurality of interactions by a plurality of users of the network system, wherein the one or more objects are matched with the natural language user request based on the token mappings; and

transmitting the matched one or more objects to the device for execution of the natural language user request based on the matched one or more objects.

2. The method of claim 1 , the natural language user request received at a social-networking system, the object graph comprising a graph comprised at least in part of interlinked social networking-objects.

3. The method of claim 1 , wherein executing the natural language user request comprises transmitting the matched one or more objects to the device for execution of the natural language user request by the device.

4. The method of claim 1 , comprising:

receiving a location of the device from the device; and

executing the natural language user request based on the matched one or more objects and the location of the device.

5. The method of claim 1 , the matched one or more objects selected from a plurality of objects in the object graph based on a proximity to a location of the device, further comprising:

receiving the location of the device from the device.

6. The method of claim 1 , the matched one or more objects comprising a business object corresponding to a business entity, the business object represented in the object graph, further comprising:

retrieving automated interaction instructions for the business entity based on the business object; and

executing the natural language user request by performing at least one of a purchase and a reservation with a network server for the business entity based on the retrieved automated interaction instructions.

7. The method of claim 1 , wherein the token mappings are generated based on a frequency with which the plurality of users associate tokens with the objects in the plurality of interactions.

8. The method of claim 1 , wherein the plurality of interactions comprise a plurality of natural language user requests from the plurality of users to the network system, wherein the token mappings are generated based on a success rate for executions of the plurality of natural language user requests.

9. An apparatus, comprising:

a processor circuit on a device;

a client service component operative on the processor circuit to receive a network query, the network query to include a natural language user request from a device and a request to match the natural language user request against an object graph;

a social object relation component operative on the processor circuit to match the natural language user request to the one or more objects in the object graph, the object graph comprising token mappings for objects within the object graph, the token mappings based on data extracted from a plurality of interactions by a plurality of users of the network system, wherein the one or more objects are matched with the natural language user request based on the token mapping; and

a network interface configured to transmit the matched one or more objects to the device for execution of the natural language user request based on the matched one or more objects.

10. The apparatus of claim 9 , the client service component operative to receive a location of the device from the device and execute the natural language user request based on the matched one or more objects and the location of the device.

11. The apparatus of claim 9 , the matched one or more objects selected from a plurality of objects in the object graph based on a proximity to a location of the device, the client service component operative to receive the location of the device from the device.

12. The apparatus of claim 9 , the matched one or more objects comprising a business object corresponding to a business entity, the business object represented in the object graph, the client service component operative to retrieve automated interaction instructions for the business entity based on the business object and execute the natural language user request by performing at least one of a purchase and a reservation with a network server for the business entity based on the retrieved automated interaction instructions.

13. The apparatus of claim 9 , wherein the token mappings are generated based on a frequency with which the plurality of users associate tokens with the objects in the plurality of interactions.

14. The apparatus of claim 9 , wherein the plurality of interactions comprise a plurality of natural language user requests from the plurality of users to the network system, wherein the token mappings are generated based on a success rate for executions of the plurality of natural language user requests.

15. At least one computer-readable storage medium comprising instructions that, when executed, cause a system to:

receive a network query at a network system, the network query to include a natural language user request from a device and a request to match the natural language user request against an object graph;

match the natural language user request to one or more objects in the object graph, the object graph comprising token mappings for objects within the object graph, the token mappings based on data extracted from a plurality of interactions by a plurality of users of the network system, wherein the one or more objects are matched with the natural language user request based on the token mappings; and

transmit the matched one or more objects to the device for execution of the natural language user request based on the matched one or more objects.

16. The computer-readable storage medium of claim 15 , comprising further instructions that, when executed, cause a system to:

receive a location of the device from the device; and

execute the natural language user request based on the matched one or more objects and the location of the device.

17. The computer-readable storage medium of claim 15 , the matched one or more objects selected from a plurality of objects in the object graph based on a proximity to a location of the device, comprising further instructions that, when executed, cause a system to:

receive the location of the device from the device.

18. The computer-readable storage medium of claim 15 , the matched one or more objects comprising a business object corresponding to a business entity, the business object represented in the object graph, comprising further instructions that, when executed, cause a system to:

retrieve automated interaction instructions for the business entity based on the business object; and

execute the natural language user request by performing at least one of a purchase and a reservation with a network server for the business entity based on the retrieved automated interaction instructions.

19. The computer-readable storage medium of claim 15 , wherein the token mappings are generated based on a frequency with which the plurality of users associate tokens with the objects in the plurality of interactions.

20. The computer-readable storage medium of claim 15 , wherein the plurality of interactions comprise a plurality of natural language user requests from the plurality of users to the network system, wherein the token mappings are generated based on a success rate for executions of the plurality of natural language user requests.