System for extracting semantic triples for building a knowledge base
The present disclosure relates to a computer-implemented method of verifying a semantic triple generated for building a knowledge base including data patterns defining concepts associated with semantic triples derived from unstructured text. The method includes providing the semantic triple to a user interface, the semantic triple including a subject, an object, and a relation. The method also includes receiving, from the user interface, an acceptance or a rejection of the subject, the object, and the relation as relevant or not to the knowledge base. The method also includes transmitting the semantic triple for inclusion as a data pattern in the knowledge base in the event that all of the subject, the object, and the relation, have been accepted.
1. A computer-implemented method of verifying a semantic triple generated for building a knowledge base including data patterns defining concepts associated with semantic triples derived from unstructured text, the method comprising:
providing the semantic triple to a user interface, the semantic triple including a subject, an object, and a relation;
receiving, from the user interface, an acceptance or a rejection of the subject, the object, and the relation as relevant or not to the knowledge base; and
transmitting the semantic triple for inclusion as a data pattern in the knowledge base in the event that all of the subject, the object, and the relation, have been accepted.
2. The method of claim 1 , further comprising storing in a database an accepted or a rejected subject, object, or relation, from a verified semantic triple.
3. The method of claim 1 , further comprising comparing the semantic triple to the database, and providing the semantic triple to the user interface if the semantic triple has not been provided to the user interface previously, and discarding the semantic triple if the triple has been accepted or rejected previously.
4. The method of claim 1 , further comprising adding a new identifier for a newly encountered entity.
5. The method of claim 1 , further comprising verifying a correctness of the semantic triple.
6. The method of claim 1 , further comprising verifying assigned phrases of the semantic triple.
7. The method of claim 1 , further comprising performing a search for candidate triples for verification.
8. A system including a processor, and a memory, the memory including instructions which, when executed by the processor, cause the processor to perform a method of verifying a semantic triple generated for building a knowledge base including data patterns defining concepts associated with semantic triples derived from unstructured text, the method comprising:
providing the semantic triple to a user interface, the semantic triple including a subject, an object, and a relation;
receiving, from the user interface, an acceptance or a rejection of the subject, the object, and the relation as relevant or not to the knowledge base; and
transmitting the semantic triple for inclusion as a data pattern in the knowledge base in the event that all of the subject, the object, and the relation, have been accepted.
9. The system of claim 8 , wherein the method further comprises storing in a database an accepted or a rejected subject, object, or relation, from a verified semantic triple.
10. The system of claim 8 , wherein the method further comprises comparing the semantic triple to the database, and providing the semantic triple to the user interface if the semantic triple has not been provided to the user interface previously, and discarding the semantic triple if the triple has been accepted or rejected previously.
11. The system of claim 8 , wherein the method further comprises adding a new identifier for a newly encountered entity.
12. The system of claim 8 , wherein the method further comprises verifying a correctness of the semantic triple.
13. The system of claim 8 , wherein the method further comprises verifying assigned phrases of the semantic triple.
14. The system of claim 8 , wherein the method further comprises performing a search for candidate triples for verification.
15. A non-transitory computer-readable medium including instructions which, when executed by a processor, cause the processor to perform a method of verifying a semantic triple generated for building a knowledge base including data patterns defining concepts associated with semantic triples derived from unstructured text, the method comprising:
providing the semantic triple to a user interface, the semantic triple including a subject, an object, and a relation;
receiving, from the user interface, an acceptance or a rejection of the subject, the object, and the relation as relevant or not to the knowledge base; and
transmitting the semantic triple for inclusion as a data pattern in the knowledge base in the event that all of the subject, the object, and the relation, have been accepted.
16. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises storing in a database an accepted or a rejected subject, object, or relation, from a verified semantic triple.
17. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises comparing the semantic triple to the database, and providing the semantic triple to the user interface if the semantic triple has not been provided to the user interface previously, and discarding the semantic triple if the triple has been accepted or rejected previously.
18. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises adding a new identifier for a newly encountered entity.
19. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises verifying a correctness of the semantic triple.
20. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises verifying assigned phrases of the semantic triple.