TECHNIQUES FOR IMPROVING INPUT TEXT PROCESSING IN A DATA PROCESSING SYSTEM THAT ANSWERS QUESTIONS

• US 20170132187A1
• Filed: 11/10/2015
• Published: 05/11/2017
• Est. Priority Date: 11/10/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: CONTRERAS, DAVID, SIZEMORE, ROBERT C., SMITH, STERLING R.
• Granted Patent: US 10,585,984 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

A technique of improving input text processing in a data processing system that answers questions includes receiving a question from a user. The question has associated supporting original input text that is utilized in answering the question. Corrective measures are applied to the supporting original input text to create supporting revised input text. The supporting revised input text documents corrective measures applied to the supporting original input text. An answer to the question is generated based on, at least in part, the supporting revised input text. The supporting original input text is recreated from the supporting revised input text based on the documented corrective measures in the supporting revised input text subsequent to generating the answer. The answer and the supporting original input text as recreated are transmitted to the user.

Claims

1. A method of improving input text processing in a data processing system that answers questions, comprising:

receiving, by a data processing system, a question from a user, wherein the question has associated supporting original input text that is utilized in answering the question;

applying, by the data processing system, corrective measures to the supporting original input text to create supporting revised input text, wherein the supporting revised input text documents corrective measures applied to the supporting original input text;

generating, by the data processing system, an answer to the question based on, at least in part, the supporting revised input text;

recreating, by the data processing system, the supporting original input text from the supporting revised input text based on the documented corrective measures in the supporting revised input text subsequent to generating the answer; and

transmitting, by the data processing system, the answer and the supporting original input text as recreated to the user.

2. The method of claim 1, further comprising:

storing the supporting revised input text in a data structure.

3. The method of claim 2, wherein the generating an answer further comprises:

performing natural language processing (NLP) on the supporting revised input text in the data structure to generate the answer.

4. The method of claim 2, wherein the data structure is a common analysis structure (CAS).

5. The method of claim 1, further comprising:

highlighting information in the recreated supporting original input text that was utilized to generate the answer.

6. The method of claim 1, wherein the corrective measures include spelling correction and abbreviation expansion.

7. The method of claim 1, wherein the corrective measures include at least one of spelling correction, abbreviation expansion, removing irrelevant information, changing anomalous forms to conforming forms, correcting bad grammar, and adding missing data.

8. A computer program product configured for improving input text processing in a data processing system that answers questions, 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 question from a user, wherein the question has associated supporting original input text that is utilized in answering the question;

apply corrective measures to the supporting original input text to create supporting revised input text, wherein the supporting revised input text documents corrective measures applied to the supporting original input text;

generate an answer to the question based on, at least in part, the supporting revised input text;

recreate the supporting original input text from the supporting revised input text based on the documented corrective measures in the supporting revised input text subsequent to generating the answer; and

transmit the answer and the supporting original input text as recreated to the user.

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

store the supporting revised input text in a data structure.

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

perform natural language processing (NLP) on the supporting revised input text in the data structure to generate the answer.

11. The computer program product of claim 9, wherein the data structure is a common analysis structure (CAS).

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

highlight information in the recreated supporting original input text that was utilized to generate the answer and is transmitted to the user.

13. The computer program product of claim 8, wherein the corrective measures include spelling correction and abbreviation expansion.

14. The computer program product of claim 8, wherein the corrective measures include at least one of spelling correction, abbreviation expansion, removing irrelevant information, changing anomalous forms to conforming forms, correcting bad grammar, and adding missing data.

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 question from a user, wherein the question has associated supporting original input text that is utilized in answering the question;

apply corrective measures to the supporting original input text to create supporting revised input text, wherein the supporting revised input text documents corrective measures applied to the supporting original input text;

generate an answer to the question based on, at least in part, the supporting revised input text;

recreate the supporting original input text from the supporting revised input text based on the documented corrective measures in the supporting revised input text subsequent to generating the answer; and

transmit the answer and the supporting original input text as recreated to the user.

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

store the supporting revised input text in a data structure.

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

perform natural language processing (NLP) on the supporting revised input text in the data structure to generate the answer.

18. The data processing system of claim 16, wherein the data structure is a common analysis structure (CAS).

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

highlight information in the recreated supporting original input text that was utilized to generate the answer and is transmitted to the user.

20. The data processing system of claim 15, wherein the corrective measures include at least one of spelling correction, abbreviation expansion, removing irrelevant information, changing anomalous forms to conforming forms, correcting bad grammar, and adding missing data.