IP Library › Granted Patent US 10,671,929
Granted Patent B2
US 10,671,929 · App. 14/472,513 · Granted Jun 2, 2020

Question correction and evaluation mechanism for a question answering system

Inventors: Branimir K. Boguraev (Bedford, NY); John P. Bufe, III (Washington, DC); Matthew T. Hatem (Portsmouth, NH); Jared M. D. Smythe (Cary, NC)
Assignee: International Business Machines Corporation
G06N5/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,671,929
App. No.
14/472,513
Granted
Jun 2, 2020
Kind
B2
Abstract

Mechanisms are provided in a question answering (QA) system comprising a QA system pipeline that analyzes an input question and generates an answer to the input question, for pre-processing the input question. The mechanisms receive an input question and input the input question to a pre-processor flow path having one or more pre-processors. The one or more pre-processors transform the input question into a transformed question by correcting errors in a formulation of the input question that are determined to be detrimental to efficient and accurate processing of the input question by a QA system pipeline of the QA system. The transformed question is then input to the QA system pipeline of the QA system which processes the transformed question to generate and output an answer to the input question.

Claims (47)

1. A method, in a question answering (QA) system comprising a QA system pipeline that analyzes an input question and generates an answer to the input question, for pre-processing the input question, the method comprising:

receiving, by the QA system, an input question for which an answer is sought by a submitter of the input question;

inputting, by the QA system, the input question to a pre-processor flow path comprising at least one pre-processor;

transforming, by the at least one pre-processor, the input question into a transformed question by correcting errors in a formulation of the input question that are determined to be detrimental to efficient and accurate processing of the input question by a QA system pipeline of the QA system, wherein the at least one pre-processor comprises a superfluous information pre-processor and a elided information pre-processor and wherein transforming the input question comprises at least one of:

identifying, by the superfluous information pre-processor that identifies superfluous information content in the input question and transforms the superfluous information content, at least one of a term, phrase, or language pattern indicative of superfluous information content in the input question that is not relevant to the underlying question being asked by the input question; and

removing, by the superfluous information pre-processor, the superfluous information content from the input question to generate a modified input question; or

identifying, by the elided information pre-processor that identifies elided information content associated with the input question and transforms the input question based on the identified elided information, at least one of a term, phrase, or language pattern indicative of elided information content in the input question that is relevant to the underlying question being asked by the input question and is missing in the input question; and

inserting, by the elided information pre-processor, the elided information content into the input question to generate the modified input question;

in response to determining that the modified input question requires reformatting, reformatting, by the at least one pre-processor, the input question into a logically and syntactically correct input question;

outputting, by the at least one pre-processor, the logically and syntactically correct input question as the transformed question;

inputting, by the at least one pre-processor, the transformed question to the QA system pipeline of the QA system; and

processing, the transformed question via the QA system pipeline to generate and output at least one answer to the input question.

2. The method of claim 1 , wherein identifying at least one of the term, phrase, or language pattern indicative of superfluous information content in the input question comprises identifying at least one of a vocative clause or a common phrase in the input question.

3. The method of claim 1 , wherein identifying at least one of the term, phrase, or language pattern indicative of the elided information content in the input question comprises identifying at least one of an elided focus, an elided verb, or an elided noun phrase.

4. The method of claim 1 , wherein inserting the elided information content into the input question to generate the modified input question comprises analyzing, by the elided information pre-processor, at least one of a domain or a context associated with the input question to determine the elided information content to be inserted into the input question.

5. A computer program product comprising a non-transitory computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device implementing a Question Answering (QA) system, causes the computing device to:

receive, by the QA system, an input question for which an answer is sought by a submitter of the input question;

input, by the QA system, the input question to a pre-processor flow path comprising at least one pre-processor;

transform, by the at least one pre-processor, the input question into a transformed question by correcting errors in a formulation of the input question that are determined to be detrimental to efficient and accurate processing of the input question by a QA system pipeline of the QA system, wherein the at least one pre-processor comprises a superfluous information pre-processor and a elided information pre-processor and wherein transforming the input question comprises at least one of:

identifying, by the superfluous information pre-processor that identifies superfluous information content in the input question and transforms the superfluous information content, at least one of a term, phrase, or language pattern indicative of superfluous information content in the input question that is not relevant to the underlying question being asked by the input question; and

removing, by the superfluous information pre-processor, the superfluous information content from the input question to generate a modified input question; or

identifying, by the elided information pre-processor that identifies elided information content associated with the input question and transforms the input question based on the identified elided information, at least one of a term, phrase, or language pattern indicative of elided information content in the input question that is relevant to the underlying question being asked by the input question and is missing in the input question; and

inserting, by the elided information pre-processor, the elided information content into the input question to generate the modified input question;

in response to determining that the modified input question requires reformatting, reformatting, by the at least one pre-processor, the input question into a logically and syntactically correct input question;

outputting, by the at least one pre-processor, the logically and syntactically correct input question as the transformed question;

input, by the at least one pre-processor, the transformed question to the QA system pipeline of the QA system; and

process, by the QA system, the transformed question via the QA system pipeline to generate and output at least one answer to the input question.

6. The computer program product of claim 5 , wherein the computer readable program further causes the computing device to identify at least one of the term, phrase, or language pattern indicative of superfluous information content in the input question at least by identifying at least one of a vocative clause or a common phrase in the input question.

7. The computer program product of claim 5 , wherein the computer readable program further causes the computing device to insert the elided information content into the input question to generate the modified input question at least by analyzing, by the elided information pre-processor, at least one of a domain or a context associated with the input question to determine the elided information content to be inserted into the input question.

8. The computer program product of claim 5 , wherein identifying at least one of the term, phrase, or language pattern indicative of the elided information content in the input question comprises at least one of an elided focus, an elided verb, or an elided noun phrase.

9. An apparatus comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor implementing a Question Answering (QA) system, cause the processor to:

receive, by the QA system, an input question for which an answer is sought by a submitter of the input question;

input, by the QA system, the input question to a pre-processor flow path comprising at least one pre-processor;

transform, by the at least one pre-processor, the input question into a transformed question by correcting errors in a formulation of the input question that are determined to be detrimental to efficient and accurate processing of the input question by a QA system pipeline of the QA system, wherein the at least one pre-processor comprises a superfluous information pre-processor and a elided information pre-processor and wherein transforming the input question comprises at least one of:

identifying, by the superfluous information pre-processor that identifies superfluous information content in the input question and transforms the superfluous information content, at least one of a term, phrase, or language pattern indicative of superfluous information content in the input question that is not relevant to the underlying question being asked by the input question; and

removing, by the superfluous information pre-processor, the superfluous information content from the input question to generate a modified input question; or

identifying, by the elided information pre-processor that identifies elided information content associated with the input question and transforms the input question based on the identified elided information, at least one of the term, phrase, or language pattern indicative of elided information content in the input question that is relevant to the underlying question being asked by the input question and is missing in the input question; and

inserting, by the elided information pre-processor, the elided information content into the input question to generate the modified input question;

in response to determining that the modified input question requires reformatting, reformatting, by the at least one pre-processor, the input question into a logically and syntactically correct input question;

outputting, by the at least one pre-processor, the logically and syntactically correct input question as the transformed question;

input, by the at least one pre-processor, the transformed question to the QA system pipeline of the QA system; and

process, by the OA system, the transformed question via the QA system pipeline to generate and output at least one answer to the input question.

10. The apparatus of claim 9 , wherein the instructions further cause the superfluous information pre-processor to identify at least one of the term, phrase, or language pattern indicative of superfluous information content in the input question at least by identifying at least one of a vocative clause or a common phrase in the input question.

11. The apparatus of claim 9 , wherein identifying at least one of the term, phrase, or language pattern indicative of the elided information content in the input question comprises at least one of an elided focus, an elided verb, or an elided noun phrase.

12. The apparatus of claim 9 , wherein the instructions further causes the elided information pre-processor to insert the elided information content into the input question to generate the modified input question at least by analyzing, by the elided information pre-processor, at least one of a domain or a context associated with the input question to determine the elided information content to be inserted into the input question.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 24, 2014
From: BOGURAEV, BRANIMIR K.; BUFE, JOHN P., III; HATEM, MATTHEW T.; SMYTHE, JARED M.D.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 033803/0282 →
Continuity (1)
Related Publication 20160062980A1 · Mar 3, 2016