SYSTEMS AND METHODS FOR NATURAL LANGUAGE PROCESSING

• US 20150261744A1
• Filed: 11/11/2014
• Published: 09/17/2015
• Est. Priority Date: 03/12/2014
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP SE
• Inventors: Sikka, Vishal, Suenbuel, Asuman, Waldinger, Richard, Richardson, Kyle
• Granted Patent: US 10,515,154 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/237 Lexical tools
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/55 Rule-based translation
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

Systems and methods are presented for performing natural language processing and reasoning. In some embodiments, a computer-implemented methods is presented. The method may include accessing a natural language query from a user, parsing the natural language query into a computer-interpretable semantic representation, converting the semantic representation into a computer-interpretable logical syntax, determining a solution to the computer-interpretable logical syntax using a reasoning engine and at least one data source, and outputting an answer to the natural language query using the solution to the computer-interpretable logical syntax.

Claims

1. A computer implemented method comprising:

accessing a natural language query from a user;

parsing the natural language query into a computer-interpretable semantic representation;

converting the semantic representation into a computer-interpretable logical syntax;

determining a solution to the computer-interpretable logical syntax using a reasoning engine and at least one data source; and

outputting an answer to the natural language query using the solution to the computer-interpretable logical syntax.

2. The method of claim 1, further comprising:

deriving a term from the natural language query that is contained neither in the reasoning engine nor in the at least one data source; and

wherein

determining the solution to the computer-interpretable logical syntax further uses the term contained neither in the reasoning engine nor in the at least one data source.

3. The method of claim 1, wherein determining the solution to the computer-interpretable logical syntax comprises:

combining information from a first data source among the at least one data source with information from a second data source among the at least one data source; and

synthesizing the combined information from the first data source and the second data source using the reasoning engine to generate the solution, wherein the solution is contained neither in the first data source nor the second data source.

4. The method of claim 1 wherein:

the natural language query comprises a plurality of questions, and

wherein an answer to a first question of the plurality of questions depends on an answer to a second question of the plurality of questions.

5. The method of claim 4, wherein determining the solution to the computer-interpretable logical syntax comprises:

determining the answer to the second question of the plurality of questions; and

determining the answer to the first question of the plurality of questions using at least the answer to the second question.

6. The method of claim 1, wherein the natural language query comprises at least one semantically ambiguous term;

and

wherein determining the solution to the computer-interpretable logical syntax further uses the semantically ambiguous term.

7. The method of claim 1, further comprising:

inferring at least two dissimilar terms in the natural language query to be semantically equivalent; and

wherein

determining the solution to the computer-interpretable logical syntax further uses the semantically equivalent inference.

8. A system comprising:

an input interface configured to access a natural language query from a user;

a processor configured to;

parse the natural language query into a computer-interpretable semantic representation;

convert the semantic representation into a computer-interpretable logical syntax;

determine a solution to the computer-interpretable logical syntax using a reasoning engine and at least one data source; and

an output interface configured to output an answer to the natural language query using the solution to the computer-interpretable logical syntax.

9. The system of claim 8, wherein the processor is further configured to:

derive a term from the natural language query that is contained neither in the reasoning engine nor in the at least one data source; and

wherein

determining the solution to the computer-interpretable logical syntax further uses the term contained neither in the reasoning engine nor in the at least one data source.

10. The system of claim 8, wherein the processor is further configured to:

combine information from a first data source among the at least one data source with information from a second data source among the at least one data source; and

synthesize the combined information from the first data source and the second data source using the reasoning engine to generate the solution, wherein the solution is contained neither in the first data source nor the second data source.

11. The system of claim 8 wherein:

the natural language query comprises a plurality of questions, and

wherein an answer to a first question of the plurality of questions depends on an answer to a second question of the plurality of questions.

12. The system of claim 11, wherein determining the solution to the computer-interpretable logical syntax comprises:

determining the answer to the second question of the plurality of questions; and

determining the answer to the first question of the plurality of questions using at least the answer to the second question.

13. The system of claim 8, wherein the natural language query comprises at least one semantically ambiguous term;

and

wherein determining the solution to the computer-interpretable logical syntax further uses the semantically ambiguous term.

14. The system of claim 8, wherein the processor is further configured to:

infer at least two dissimilar terms in the natural language query to be semantically equivalent; and

wherein

determining the solution to the computer-interpretable logical syntax further uses the semantically equivalent inference.

15. A computer-readable medium embodying instructions that, when executed by a processor perform operations comprising:

accessing a natural language query from a user;

parsing the natural language query into a computer-interpretable semantic representation;

converting the semantic representation into a computer-interpretable logical syntax;

determining a solution to the computer-interpretable logical syntax using a reasoning engine and at least one data source; and

outputting an answer to the natural language query using the solution to the computer-interpretable logical syntax.

16. The computer-readable medium of claim 15, wherein the instructions further cause the processor to perform operations comprising:

deriving a term from the natural language query that is contained neither in the reasoning engine nor in the at least one data source; and

wherein

determining the solution to the computer-interpretable logical syntax further uses the term contained neither in the reasoning engine nor in the at least one data source.

17. The computer-readable medium of claim 15, wherein determining the solution to the computer-interpretable logical syntax comprises:

combining information from a first data source among the at least one data source with information from a second data source among the at least one data source; and

synthesizing the combined information from the first data source and the second data source using the reasoning engine to generate the solution, wherein the solution is contained neither in the first data source nor the second data source.

18. The computer-readable medium of claim 15 wherein:

the natural language query comprises a plurality of questions, and

wherein an answer to a first question of the plurality of questions depends on an answer to a second question of the plurality of questions.

19. The computer-readable medium of claim 18, wherein determining the solution to the computer-interpretable logical syntax comprises:

determining the answer to the second question of the plurality of questions; and

determining the answer to the first question of the plurality of questions using at least the answer to the second question.

20. The computer-readable medium of claim 15, wherein the natural language query comprises at least one semantically ambiguous term;

and

wherein determining the solution to the computer-interpretable logical syntax further uses the semantically ambiguous term.