RECOMBINATION TECHNIQUES FOR NATURAL LANGUAGE GENERATION

• US 20170091170A1
• Filed: 09/25/2015
• Published: 03/30/2017
• Est. Priority Date: 09/25/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: CARDILLO, BRYAN D.
• Granted Patent: US 10,325,026 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/90332 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 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/56 Natural language generation

Abstract

A technique for generating a new equivalent phrase for an input phrase includes receiving a first input phrase for natural language expansion. Tokens that correspond to parts of speech are generated for the first input phrase. An original grammar tree is generated using at least some of the tokens. One or more alternate grammar trees are generated that are different from the original grammar tree but substantially equivalent to the original grammar tree. One or more synonyms for at least one of the tokens are generated. Finally, one or more new phrases are generated based on the one or more alternate grammar trees and the one or more synonyms.

Claims

1. A method of generating one or more new equivalent phrases for an input phrase, comprising:

receiving, by a data processing system, a first input phrase for natural language expansion;

generating, by the data processing system, tokens that correspond to parts of speech for the first input phrase;

generating, by the data processing system, an original grammar tree using at least some of the tokens;

generating, by the data processing system, one or more alternate grammar trees that are different from the original grammar tree but substantially equivalent to the original grammar tree;

generating, by the data processing system, one or more synonyms for at least one of the tokens; and

generating, by the data processing system, one or more new phrases based on the one or more alternate grammar trees and the one or more synonyms.

2. The method of claim 1, further comprising:

tagging, by the data processing system, the parts of speech prior to the generating the original grammar tree.

3. The method of claim 2, wherein the tagging further comprises:

indicating whether the tokens correspond to one of a noun, a verb, an adjective, an adverb, and a pronoun.

4. The method of claim 1, wherein the first input phrase is a question, the one or more new phrases are questions, and the method further comprises:

receiving, by the data processing system, the one or more new phrases as input;

generating, by the data processing system, one or more answers to the one or more new phrases; and

determining, by the data processing system, whether the one or more answers are substantially similar to an answer generated for the first input phrase.

5. The method of claim 1, wherein the first input phrase is a question, the one or more new phrases are answers to the question, and the method further comprises:

determining, by the data processing system, whether the one or more new phrases are substantially similar.

6. The method of claim 1, wherein the first input phrase is a question and the one or more new phrases are questions.

7. The method of claim 1, wherein the first input phrase is a question and the one or more new phrases are answers to the question.

8. A computer program product configured to transform questions for a question answering (QA) system, the computer program product comprising:

a computer-readable storage device; and

computer-readable program code embodied on the computer-readable storage device, wherein the computer-readable program code, when executed by a data processing system, causes the data processing system to;

receive a first input phrase for natural language expansion;

generate tokens that correspond to parts of speech for the first input phrase;

generate an original grammar tree using at least some of the tokens;

generate one or more alternate grammar trees that are different from the original grammar tree but substantially equivalent to the original grammar tree;

generate one or more synonyms for at least one of the tokens; and

generate one or more new phrases based on the one or more alternate grammar trees and the one or more synonyms.

9. The computer program product of claim 8, wherein the computer-readable program code, when executed by the data processing system, further configures the data processing system to:

tag the parts of speech prior to the generating the original grammar tree.

10. The computer program product of claim 9, wherein the computer-readable program code, when executed by the data processing system, further configures the data processing system to:

indicate whether the tokens correspond to one of a noun, a verb, an adjective, an adverb, and a pronoun.

11. The computer program product of claim 8, wherein the first input phrase is a question, the one or more new phrases are questions, and the computer-readable program code, when executed by the data processing system, further configures the data processing system to:

receive the one or more new phrases as input;

generate one or more responses to the one or more new phrases; and

determine whether the one or more responses are substantially similar to a response generated for the first input phrase.

12. The computer program product of claim 8, wherein the first input phrase is a question, the one or more new phrases are answers to the question, and the computer-readable program code, when executed by the data processing system, further configures the data processing system to:

determine whether the one or more new phrases are substantially similar.

13. The computer program product of claim 8, wherein the first input phrase is a question and the one or more new phrases are questions.

14. The computer program product of claim 8, wherein the first input phrase is a question and the one or more new phrases are answers to the question.

15. A data processing system, comprising:

a cache memory; and

a processor coupled to the cache memory, wherein the processor is configured to;

receive a first input phrase for natural language expansion;

generate tokens that correspond to parts of speech for the first input phrase;

generate an original grammar tree using at least some of the tokens;

generate one or more alternate grammar trees that are different from the original grammar tree but substantially equivalent to the original grammar tree;

generate one or more synonyms for at least one of the tokens; and

generate one or more new phrases based on the one or more alternate grammar trees and the one or more synonyms.

16. The data processing system of claim 15, wherein the processor is further configured to:

tag the parts of speech prior to the generating the original grammar tree.

17. The data processing system of claim 16, wherein the processor is further configured to:

indicate whether the tokens correspond to one of a noun, a verb, an adjective, an adverb, and a pronoun.

18. The data processing system of claim 15, wherein the processor is further configured to:

receive the one or more new phrases as input;

generate one or more responses to the one or more new phrases; and

determine whether the one or more responses are substantially similar to a response generated for the first input phrase.

19. The data processing system of claim 15, wherein the processor is further configured to:

determine whether the one or more new phrases are substantially similar.

20. The data processing system of claim 15, wherein the first input phrase is a question and the one or more new phrases are questions.