Techniques for graph based natural language processing
Techniques for graph based natural language processing are described. In one embodiment an apparatus may comprise a client service component operative on the processor circuit to receive a natural language user request from a device and to execute the natural language user request based on matched one or more objects and a social object relation component operative on the processor circuit to match the natural language user request to the one or more objects in an 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. Other embodiments are described and claimed.
1. A computer-implemented method, comprising:
receiving a natural language user request at a client device;
matching the natural language user request to one or more local objects in a local object graph stored on the client device, 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 a network system, wherein the one or more objects are matched with the natural language user request based on the token mappings; and
executing the natural language user request based on the matched one or more local objects.
2. The method of claim 1 , the local objects stored on the client device prior to receiving the natural language user request.
3. The method of claim 1 , the local objects comprising a cached object from an object graph stored on a network system.
4. The method of claim 1 , the local objects comprising at least one object not represented in an object graph stored on a network system.
5. The method of claim 1 , at least one of the local objects being stored in a local object store on the client device, and at least one of the local objects being stored in a source on the client device distinct from the local object store.
6. The method of claim 1 , at least one of the local objects retrieved or generated based on local data stored on the client device.
7. The method of claim 1 , further comprising determining a confidence level that one of the local objects corresponds to a natural language meaning of the user request and that the local object corresponds to an intent of the user request.
8. An apparatus, comprising:
a processor circuit on a mobile device;
a client service component operative on the processor circuit to receive a natural language user request;
a social object relation component operative on the processor circuit to match the natural language user request to one or more local objects in a local object graph stored on the client device, 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
an execution component operative on the processor circuit configured to execute the natural language user request based on the matched one or more local objects.
9. The apparatus of claim 8 , the local objects stored on the client device prior to receiving the natural language user request.
10. The apparatus of claim 8 , the local objects comprising a cached object from an object graph stored on a network system.
11. The apparatus of claim 8 , the local objects comprising at least one object not represented in an object graph stored on a network system.
12. The apparatus of claim 8 , at least one of the local objects being stored in a local object store on the client device, and at least one of the local objects being stored in a source on the client device distinct from the local object store.
13. The apparatus of claim 8 , at least one of the local objects retrieved or generated based on local data stored on the client device.
14. The apparatus of claim 8 , the processor circuit further configured to determine a confidence level that one of the local objects corresponds to a natural language meaning of the user request and that the local object corresponds to an intent of the user request.
15. At least one non-transitory computer-readable storage medium comprising instructions that, when executed, cause a system to:
receive a natural language user request at a client device;
match the natural language user request to one or more local objects in a local object graph stored on the client device, 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 a network system, wherein the one or more objects are matched with the natural language user request based on the token mappings; and
execute the natural language user request based on the matched one or more local objects.
16. The medium of claim 15 , the local objects stored on the client device prior to receiving the natural language user request.
17. The medium of claim 15 , the local objects comprising at least one of a cached object from an object graph stored on a network system, or an object not represented in the object graph stored on the network system.
18. The medium of claim 15 , at least one of the local objects being stored in a local object store on the client device, and at least one of the local objects being stored in a source on the client device distinct from the local object store.
19. The medium of claim 15 , at least one of the local objects retrieved or generated based on local data stored on the client device.
20. The medium of claim 15 , further comprising determining a confidence level that one of the local objects corresponds to a natural language meaning of the user request and that the local object corresponds to an intent of the user request.