Translating Structured Languages to Natural Language Using Domain-Specific Ontology

• US 20180210879A1
• Filed: 01/23/2017
• Published: 07/26/2018
• Est. Priority Date: 01/23/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Mittal, Ashish R., Saha, Diptikalyan, Sankaranarayanan, Karthik
• Granted Patent: US 10,169,336 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/90344 by using string matching techniques
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/51 Translation evaluation
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

Methods, systems, and computer program products for translating structured languages to natural language using domain-specific ontology are provided herein. A computer-implemented method includes determining similarities among multiple natural language query interpretations derived from an input query, determining differences among the multiple natural language query interpretations, and generating natural language descriptions of each of the multiple natural language query interpretations based on analysis of the determined similarities, the determined differences, and the input query. The method also includes producing, for each of the natural language query interpretations, a natural language string that represents one or more unambiguous interpretations of the input query, wherein the producing comprises consolidating the generated natural language descriptions. Further, the method includes outputting each of the produced natural language strings to a user.

Claims

1. A computer-implemented method, comprising:

determining one or more similarities among multiple natural language query interpretations derived from an input query;

determining one or more differences among the multiple natural language query interpretations derived from the input query;

generating one or more natural language descriptions of each of the multiple natural language query interpretations based on analysis of (i) the one or more determined similarities, (ii) the one or more determined differences, and (iii) the input query;

producing, for each of the multiple natural language query interpretations, a natural language string that represents one or more unambiguous interpretations of the input query, wherein said producing comprises consolidating the generated natural language descriptions; and

outputting each of the produced natural language strings to a user;

wherein the steps are carried out by at least one computing device.

2. The computer-implemented method of claim 1, comprising:

providing the one or more generated natural language descriptions to a user responsible for submitting the input query.

3. The computer-implemented method of claim 1, wherein the one or more generated natural language descriptions comprise one or more structured natural language components.

4. The computer-implemented method of claim 3, wherein the one or more structured natural language components comprise a common sequence of one or more words common to each of the multiple natural language query interpretations.

5. The computer-implemented method of claim 3, wherein the one or more structured natural language components comprise one or more sequences of one or more words that are distinct to each of the multiple natural language query interpretations.

6. The computer-implemented method of claim 1, wherein said outputting comprises outputting each produced natural language string to a user responsible for submitting the input query.

7. The computer-implemented method of claim 1, comprising:

generating the multiple natural language query interpretations by translating one or more structured language query interpretations to natural language using one or more domain-specific ontologies.

8. The computer-implemented method of claim 7, wherein each of the one or more ontologies comprises a descriptive model that includes a set of (i) one or more object types, (ii) one or more properties, and (iii) one or more relationship types.

9. The computer-implemented method of claim 7, comprising:

storing the generated natural language query interpretations in a database.

10. The computer-implemented method of claim 1, comprising:

generating the multiple natural language query interpretations by translating one or more structured language query interpretations to natural language using one or more graph-based semantic representations.

11. The computer-implemented method of claim 10, wherein each of the one or more graph-based semantic representations comprises a semantic network containing one or more facts about one or more relationships between one or more different objects.

12. The computer-implemented method of claim 10, comprising:

storing the generated natural language query interpretations in a database.

13. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:

determine one or more similarities among multiple natural language query interpretations derived from an input query;

determine one or more differences among the multiple natural language query interpretations derived from the input query;

generate one or more natural language descriptions of each of the multiple natural language query interpretations based on analysis of (i) the one or more determined similarities, (ii) the one or more determined differences, and (iii) the input query;

produce, for each of the multiple natural language query interpretations, a natural language string that represents one or more unambiguous interpretations of the input query, wherein said producing comprises consolidating the generated natural language descriptions; and

output each of the produced natural language strings to a user.

14. The computer program product of claim 13, wherein the program instructions executable by a computing device further cause the computing device to:

provide the one or more generated natural language descriptions to a user responsible for submitting the input query.

15. The computer program product of claim 13, wherein the one or more generated natural language descriptions comprise one or more structured natural language components.

16. The computer program product of claim 15, wherein the one or more structured natural language components comprise a common sequence of one or more words common to each of the multiple natural language query interpretations.

17. The computer program product of claim 15, wherein the one or more structured natural language components comprise one or more sequences of one or more words that are distinct to each of the multiple natural language query interpretations.

18. The computer program product of claim 13, wherein said outputting comprises outputting each produced natural language string to a user responsible for submitting the input query.

19. A system comprising:

a memory; and

at least one processor operably coupled to the memory and configured for;

determining one or more similarities among multiple natural language query interpretations derived from an input query;

determining one or more differences among the multiple natural language query interpretations derived from the input query;

generating one or more natural language descriptions of each of the multiple natural language query interpretations based on analysis of (i) the one or more determined similarities, (ii) the one or more determined differences, and (iii) the input query;

producing, for each of the multiple natural language query interpretations, a natural language string that represents one or more unambiguous interpretations of the input query, wherein said producing comprises consolidating the generated natural language descriptions; and

outputting each of the produced natural language strings to a user.

20. A computer-implemented method, comprising:

generating one or more structured language query interpretations of a query inputted by a user;

translating the one or more structured language query interpretations to natural language using one or more domain-specific ontologies;

determining (i) one or more similarities among the natural language query interpretations and (ii) one or more differences among the natural language query interpretations;

generating one or more natural language descriptions of each of the multiple natural language query interpretations based on analysis of (i) the one or more determined similarities, (ii) the one or more determined differences, and (iii) the query;

producing, for each of the multiple natural language query interpretations, a natural language string that represents one or more unambiguous interpretations of the query, wherein said producing comprises consolidating the generated natural language descriptions; and

outputting each of the produced natural language strings to a user;

wherein the steps are carried out by at least one computing device.