Question answering system-based generation of distractors using machine learning

Patent metadata

Field	Value
Publication number	US-10789552-B2
Application number	US-201916534370-A
Country	US
Kind code	B2
Filing date	Aug 7, 2019
Priority date	Mar 30, 2015
Publication date	Sep 29, 2020
Grant date	Sep 29, 2020

Abstract

Generating distractors for text-based MCT items. An MCT item stem is received. The stem is transmitted to a QA system and a plurality of candidate answers related to the stem is received from the QA system. Incorrect answers in the plurality of candidate answers are identified. Textual features are extracted from the stem. A set of semantic criteria associated with the extracted textual features is generated. Based on the generated semantic criteria, a subset of the incorrect candidate answers is selected.

First claim

What is claimed is:

1. A method for generating distractors for text-based multiple choice test (MCT) items, the method comprising:
receiving, by a computer, an MCT item stem and a key;
submitting, by the computer, the stem to a question answering (QA) system wherein a QA system generates a list of candidate answers to the query;
in response to submitting the stem to the QA system, receiving, by the computer, from the QA system a plurality of candidate answers;
identifying, by the computer, one or more incorrect candidate answers in the plurality of candidate answers;
extracting, by the computer, textual features from the stem, wherein the textual features are one or more of a term in the stem or a concept semantically related to the term in the stem;
applying, by the computer, a machine learning model to generate a set of semantic criteria associated with the extracted textual features;
selecting, by the computer, as distractors the one or more of the incorrect candidate answers, that satisfy the generated semantic criteria; and
creating, by the computer, an MCT item that comprises the stem, the key, and the distractors.

2. The method of claim 1 , wherein the stem is one of: a question to be answered, a problem to be solved, or an incomplete statement to be completed.

3. The method of claim 1 , wherein the MCT item stem comprises a predefined number of alternative choices, and the plurality of candidate answers is at least the predefined number of alternative choices that is less than a predefined maximum number.

4. The method of claim 1 , wherein identifying, by the computer, incorrect answers comprises:
identifying, by the computer, a correct answer by comparing the plurality of candidate answers with the key; and
deleting, by the computer, the correct answer from the plurality of candidate answers.

5. The method of claim 1 , wherein generating the set of semantic criteria associated with the extracted textual features comprises:
applying, by the computer, a trained machine learning model to the extracted textual features, using a predefined set of semantic criteria; and
refining, by the computer, the set of semantic criteria by applying a predefined set of rules.

6. The method of claim 5 , wherein applying, by the computer, a trained machine learning model further comprises using, by the computer, multi-label classification.

7. The method of claim 1 , wherein selecting a subset of the incorrect candidate answers, based on the generated semantic criteria, comprises:
generating, by the computer, hypotheses concerning the semantic criteria and the incorrect candidate answers;
collecting, by the computer, evidence supporting or refuting each hypothesis;
assigning, by the computer, to each hypothesis a numerical value representing a degree to which the evidence justifies or refutes the hypothesis; and
selecting, by the computer, the subset of the incorrect candidate answers based on the numerical value.

8. A computer system for generating distractors for text-based multiple choice test (MCT) items, the computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:

receiving, by a computer, an MCT item stem and a key;
submitting, by the computer, the stem to a question answering (QA) system wherein a QA system generates a list of candidate answers to the query;
in response to submitting the stem to the QA system, receiving, by the computer, from the QA system a plurality of candidate answers;
identifying, by the computer, one or more incorrect candidate answers in the plurality of candidate answers;
extracting, by the computer, textual features from the stem, wherein the textual features are one or more of a term in the stem or a concept semantically related to the term in the stem;
applying, by the computer, a machine learning model to generate a set of semantic criteria associated with the extracted textual features;
selecting, by the computer, as distractors the one or more of the incorrect candidate answers, that satisfy the generated semantic criteria; and
creating, by the computer, an MCT item that comprises the stem, the key, and the distractors.

9. The computer system of claim 8 , wherein the stem is one of: a question to be answered, a problem to be solved, or an incomplete statement to be completed.

10. The computer system of claim 8 , wherein the MCT item stem comprises a predefined number of alternative choices, and the plurality of candidate answers is at least the predefined number of alternative choices that is less than a predefined maximum number.

11. The computer system of claim 8 , wherein identifying, by the computer, incorrect answers comprises:
identifying, by the computer, a correct answer by comparing the plurality of candidate answers with the key; and
deleting, by the computer, the correct answer from the plurality of candidate answers.

12. The computer system of claim 8 , wherein generating the set of semantic criteria associated with the extracted textual features comprises:
applying, by the computer, a trained machine learning model to the extracted textual features, using a predefined set of semantic criteria; and
refining, by the computer, the set of semantic criteria by applying a predefined set of rules.

13. The computer system of claim 12 , wherein applying, by the computer, a trained machine learning model further comprises using, by the computer, multi-label classification.

14. The computer system of claim 8 , wherein selecting a subset of the incorrect candidate answers, based on the generated semantic criteria, comprises:
generating, by the computer, hypotheses concerning the semantic criteria and the incorrect candidate answers;
collecting, by the computer, evidence supporting or refuting each hypothesis;
assigning, by the computer, to each hypothesis a numerical value representing a degree to which the evidence justifies or refutes the hypothesis; and
selecting, by the computer, the subset of the incorrect candidate answers based on the numerical value.

15. A computer program product for generating distractors for text-based multiple choice test (MCT) items, the computer program product comprising:
one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more tangible storage medium, the program instructions executable by a processor, the program instructions comprising:
program instructions to receive an MCT item stem and a key;
program instructions to submit the stem to a question answering (QA) system wherein a QA system generates a list of candidate answers to the query;
in response to submitting the stem to the QA system, program instructions to receive from the QA system a plurality of candidate answers;
program instructions to identify one or more incorrect candidate answers in the plurality of candidate answers;
program instructions to extract textual features from the stem, wherein the textual features are one or more of a term in the stem or a concept semantically related to the term in the stem;
program instructions to apply a machine learning model to generate a set of semantic criteria associated with the extracted textual features;
program instructions to se

Assignees

• IBM

Inventors

• Agarwalla Lalit
• Mungi Ashish
• Mustafi Joy
• Parikh Ankur

Classifications

• G06N20/00 Primary

  Machine learning · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F16/90332

  Natural language query formulation or dialogue systems · CPC title

• G09B7/06

  of the multiple-choice answer-type, i.e. where a given question is provided with a series of answers and a choice has to be made from the answers · CPC title