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;
matching the natural language user request to one or more objects in an object graph, the object graph comprising one or more token mappings matching one or more objects in the object graph, the natural language user request matched to the one or more objects based on the one or more token mappings; and
returning the matched at least one object in response to the natural language user request.
2. The method of claim 1 , the object graph comprising token mappings for the one or more objects generated based on a plurality of interactions by a plurality of users with a network system, 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.
3. The method of claim 1 , the object graph comprising one or more objects representing at least one of:
a relationship between natural language words,
a semantic understanding between the natural language words, or
a correlation between the natural language words and the semantic understanding.
4. The method of claim 1 , the natural language user request received at a network system.
5. The method of claim 1 , the natural language user request received at a client device.
6. The method of claim 1 , further comprising executing the natural language user request by a client device based on the matched objects.
7. The method of claim 1 , the object graph comprising token mappings for the one or more objects, wherein the token mappings are generated based on a frequency with which the plurality of users associate tokens with the objects in a plurality of interactions.
8. An apparatus, comprising:
a processor circuit on a 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 objects in an object graph, the object graph comprising one or more token mappings matching one or more objects in the object graph, the natural language user request matched to the one or more objects based on the one or more token mappings; and
an interface configured to return the matched at least one object in response to the natural language user request.
9. The apparatus of claim 8 , the object graph comprising token mappings for the one or more objects, wherein the token mappings are generated based on a frequency with which the plurality of users associate tokens with the objects in a plurality of interactions.
10. The apparatus of claim 8 , the object graph comprising token mappings for the one or more objects generated based on a plurality of interactions by a plurality of users with a network system, 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.
11. The apparatus of claim 8 , the object graph comprising one or more objects representing at least one of:
a relationship between natural language words,
a semantic understanding between the natural language words, or
a correlation between the natural language words and the semantic understanding.
12. The apparatus of claim 8 , the natural language user request received at one of a network system or a client device.
13. At least one non-transitory computer-readable storage medium comprising instructions that, when executed, cause a system to:
receive a natural language user request;
match the natural language user request to one or more objects in an object graph, the object graph comprising one or more token mappings matching one or more objects in the object graph, the natural language user request matched to the one or more objects based on the one or more token mappings; and
return the matched at least one object in response to the natural language user request.
14. The medium of claim 13 , the object graph comprising one or more objects representing at least one of:
a relationship between natural language words,
a semantic understanding between the natural language words, or
a correlation between the natural language words and the semantic understanding.
15. The medium of claim 13 , the natural language user request received at a network system or a client device.
16. The medium of claim 13 , the object graph comprising token mappings for the one or more objects, wherein the token mappings are generated based on a frequency with which the plurality of users associate tokens with the objects in a plurality of interactions.
17. The medium of claim 13 , the object graph comprising token mappings for the one or more objects generated based on a plurality of interactions by a plurality of users with a network system, 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.