Question answering to populate knowledge base

• US 10,108,700 B2
• Filed: 03/15/2013
• Issued: 10/23/2018
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Gupta, Rahul, Sun, Shaohua, Blitzer, John, Lin, Dekang, Gabrilovich, Evgeniy
• Primary Examiner(s): Al Hashemi, Sana A
• Application Number:
  US13/842,606
• Publication Number:
  US 20140280307A1
• Time in Patent Office: 2,048 Days
• Field of Search: 707687, 707705, 707790, 707813, 707821, 707964
• CPC Class Codes: G06F 16/3331 Query processing
• CPC Class Codes: G06N 5/025 Extracting rules from data

Abstract

Methods and systems are provided for a question answering. In some implementations, a data element to be updated is identified in a knowledge graph and a query is generated based at least in part on the data element. The query is provided to a query processing engine. Information is received from the query processing engine in response to the query. The knowledge graph is updated based at least in part on the received information.

Claims

1. A computer implemented method comprising the following operations performed by one or more processors:

identifying, by one or more of the processors, an entity reference in a knowledge graph, wherein the entity reference corresponds to an entity type;

identifying, by one or more of the processors, a missing data element associated with the entity reference, the missing data element reflecting a property of the entity reference for which no property value is currently assigned;

generating, automatically by one or more of the processors in response to identifying the missing data element associated with the entity reference, a query based at least in part on the missing data element and the entity type;

providing, by one or more of the processors, the query to a query processing engine;

receiving information from the query processing engine in response to the query; and

updating, by one or more of the processors in response to receiving information from the query processing engine, the knowledge graph based at least in part on the received information.

2. The method of claim 1, wherein identifying a missing data element comprises:

comparing properties associated with the entity reference to a schema table associated with the entity type; and

determining that the schema table includes the property of the entity reference for which no value is currently assigned.

3. The method of claim 1, wherein generating the query comprises generating a natural language query.

4. The method of claim 1, wherein generating the query comprises selecting, from the knowledge graph, disambiguation query terms associated with the entity reference, wherein the disambiguation query terms comprise property values associated with the entity reference, and wherein the query includes the disambiguation query terms and one or more terms associated with the missing data element.

5. The method of claim 1, wherein generating the query comprises selecting, from the knowledge graph, disambiguation query terms associated with the entity reference, wherein the disambiguation query terms comprise properties associated with the entity reference, and wherein the query includes the disambiguation query terms and one or more terms associated with the missing data element.

6. The method of claim 1, wherein updating the knowledge graph comprises updating the data graph to include information in place of the missing data element.

7. A system comprising:

one or more computers configured to perform operations comprising;

identifying, by one or more of the computers, an entity reference in a knowledge graph, wherein the entity reference corresponds to an entity type;

identifying, by one or more of the computers, a missing data element associated with the entity reference, the missing data element reflecting a property of the entity reference for which no property value is currently assigned;

generating, automatically by one or more of the computers in response to identifying the missing data element associated with the entity reference, a query based at least in part on the missing data element and the entity type;

providing, by one or more of the computers, the query to a query processing engine;

receiving information from the query processing engine in response to the query; and

updating, by one or more of the computers in response to receiving information from the query processing engine, the knowledge graph based at least in part on the received information.

8. The system of claim 7, wherein identifying a missing data element comprises:

comparing properties associated with the entity reference to a schema table associated with the entity type; and

determining that the schema table includes the property of the entity reference for which no value is currently assigned.

9. The system of claim 7, wherein generating the query comprises generating a natural language query.

10. The system of claim 7, wherein generating the query comprises selecting, from the knowledge graph, disambiguation query terms associated with the entity reference, wherein the disambiguation query terms comprise property values associated with the entity reference, and wherein the query includes the disambiguation query terms and one or more terms associated with the missing data element.

11. The system of claim 7, wherein generating the query comprises selecting, from the knowledge graph, disambiguation query terms associated with the entity reference, wherein the disambiguation query terms comprise properties associated with the entity reference, and wherein the query includes the disambiguation query terms and one or more terms associated with the missing data element.

12. The system of claim 7, wherein updating the knowledge graph comprises updating the data graph to include information in place of the missing data element.

13. A computer-implemented method comprising the following operations performed by one or more processors:

identifying, by one or more of the processors, a data element in a knowledge graph to be updated based at least in part on a query record, wherein the identified element is determined to be outdated based on a conflict between the query record and a property value in the knowledge graph;

generating, automatically by one or more of the processors in response to identifying the data element in the knowledge graph to be updated, a query based at least in part on the outdated element;

providing, by one or more of the processors, the query to a query processing engine;

receiving, by one or more of the processors, information from the query processing engine in response to the query; and

updating, by one or more of the processors in response to receiving information from the query processing engine, the knowledge graph based at least in part on the received information.

14. The method of claim 13, wherein the query record comprises data associated with one or more previously performed searches.

15. The method of claim 13, wherein generating the query comprises generating a natural language query.

16. The method of claim 13, wherein generating the query comprises selecting, from the knowledge graph, disambiguation query terms associated with the entity reference, wherein the disambiguation query terms comprise property values associated with the entity reference, and wherein the query includes the disambiguation query terms and one or more terms associated with the outdated data element.

17. The method of claim 13, wherein generating the query comprises selecting, from the knowledge graph, disambiguation query terms associated with the entity reference, wherein the disambiguation query terms comprise properties associated with the entity reference, and wherein the query includes the disambiguation query terms and one or more terms associated with the outdated data element.

18. The method of claim 13, wherein updating the knowledge graph comprises updating the data graph to include information in place of the outdated data element.

19. A system comprising:

one or more computers configured to perform operations comprising;

identifying, by one or more of the computers, a data element in a knowledge graph to be updated based at least in part on a query record, wherein the identified element is determined to be outdated based on a conflict between the query record and a property value in the knowledge graph;

generating, automatically by one or more of the computers in response to identifying the data element in the knowledge graph to be updated, a query based at least in part on the outdated element;

providing, by one or more of the computers, the query to a query processing engine;

receiving information from the query processing engine in response to the query; and

updating, by one or more of the computers in response to receiving information from the query processing engine, the knowledge graph based at least in part on the received information.

20. The system of claim 19, wherein the query record comprises data associated with one or more previously performed searches.

21. The system of claim 19, wherein generating the query comprises generating a natural language query.

22. The system of claim 19, wherein generating the query comprises selecting, from the knowledge graph, disambiguation query terms associated with the entity reference, wherein the disambiguation query terms comprise property values associated with the entity reference, and wherein the query includes the disambiguation query terms and one or more terms associated with the outdated data element.

23. The system of claim 19, wherein generating the query comprises selecting, from the knowledge graph, disambiguation query terms associated with the entity reference, wherein the disambiguation query terms comprise properties associated with the entity reference, and wherein the query includes the disambiguation query terms and one or more terms associated with the outdated data element.

24. The system of claim 19, wherein updating the knowledge graph comprises updating the data graph to include information in place of the identified data element.