Learning unfamiliar measurement units in a deep question answering system

Patent metadata

Field	Value
Publication number	US-11475339-B2
Application number	US-201916557366-A
Country	US
Kind code	B2
Filing date	Aug 30, 2019
Priority date	Aug 30, 2019
Publication date	Oct 18, 2022
Grant date	Oct 18, 2022

Abstract

A method utilizes a deep question answering (QA) system to provide an answer, to a certain type of question, that includes an unfamiliar measurement unit. An answer key is utilized to train a DeepQA system to search for passages that answer a certain type of question, where the DeepQA system outputs an answer key value and an answer key measurement unit that is associated with the answer key value. The method identifies a candidate answer that includes a candidate passage containing the answer key value but not the answer key measurement unit, where a candidate passage measurement unit in the candidate passage is associated with the answer key value. The method then matches the answer key measurement unit to the candidate passage measurement unit based on the answer key measurement unit and the candidate passage measurement unit both being associated with the answer key value.

First claim

What is claimed is:

1. A method comprising:
utilizing an answer key to train a deep question answering (DeepQA) system to search for passages that answer a certain type of question, wherein the DeepQA system outputs an answer key value and an answer key measurement unit that is associated with the answer key value;
identifying a candidate answer that includes a candidate passage containing the answer key value but not the answer key measurement unit, wherein a candidate passage measurement unit in the candidate passage is associated with the answer key value, and wherein the candidate passage measurement unit is a measurement unit that is different from the answer key measurement unit;
matching the answer key measurement unit to the candidate passage measurement unit based on the answer key measurement unit and the candidate passage measurement unit both being associated with the answer key value;
retraining the DeepQA system to retrieve answers, for the certain type of question, that include one or more of the answer key measurement unit and the candidate passage measurement unit, wherein retrained DeepQA system controls a physical aircraft;
receiving, by the retrained DeepQA system, the certain type of question;
retrieving, by the retrained DeepQA system, a passage that includes the answer key value and one or more of the answer key measurement unit and the candidate passage measurement unit;
answering, by the retrained DeepQA system, the certain type of question with the passage that includes the answer key value and one or more of the answer key measurement unit and the candidate passage measurement unit;
recognizing, by the retrained DeepQA system, that the physical aircraft is flying below an identified minimum approach speed while landing, wherein the minimum approach speed is identified by the retrained DeepQA system, and wherein an auto-assist hydraulic system is required to control a rudder of the physical aircraft if the physical aircraft is flying below the identified minimum approach speed while landing; and
in response to recognizing that the physical aircraft is flying below the identified minimum approach speed while landing, automatically activating, by the retrained DeepQA system, the auto-assist hydraulic system to control a rudder of the physical aircraft while the physical aircraft is landing.

2. The method of claim 1 , wherein the answer key value in the answer key and the answer key value in the candidate passage are exact matches.

3. The method of claim 1 , wherein the answer key value in the answer key and the answer key value in the candidate passage have different values that are within a predefined range.

4. The method of claim 1 , further comprising:
analyzing the certain type of question to determine a lexical answer type (LAT) for the certain type of question;
matching the LAT to the candidate passage measurement unit; and
selecting an answer to the certain type of question based on the matching of the LAT to the candidate passage measurement unit.

5. The method of claim 1 , further comprising:
assigning an uncertainty value of the answer key measurement unit matching the candidate passage measurement unit; and
generating answers to the certain type of question utilizing terms that have the assigned uncertainty value.

6. The method of claim 1 , wherein the answer key utilizes one or more ground truth measurement units for the answer key measurement unit.

7. A computer program product comprising a computer readable storage medium having program code embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, and wherein the program code is readable and executable by a processor to perform a method comprising:
utilizing an answer key to train a deep question answering (QA) system to search for passages that answer a certain type of question, wherein the DeepQA system outputs an answer key value and an answer key measurement unit that is associated with the answer key value;
identifying a candidate answer that includes a candidate passage containing the answer key value but not the answer key measurement unit, wherein a candidate passage measurement unit in the candidate passage is associated with the answer key value, and wherein the candidate passage measurement unit is a measurement unit that is different from the answer key measurement unit;
matching the answer key measurement unit to the candidate passage measurement unit based on the answer key measurement unit and the candidate passage measurement unit both being associated with the answer key value;
retraining the DeepQA system to retrieve answers, for the certain type of question, that include one or more of the answer key measurement unit and the candidate passage measurement unit, wherein retrained DeepQA system controls a physical aircraft;
receiving, by the retrained DeepQA system, the certain type of question;
retrieving, by the retrained DeepQA system, a passage that includes the answer key value and one or more of the answer key measurement unit and the candidate passage measurement unit;
answering, by the retrained DeepQA system, the certain type of question with the passage that includes the answer key value and one or more of the answer key measurement unit and the candidate passage measurement unit;
recognizing, by the retrained DeepQA system, that the physical aircraft is flying below an identified minimum approach speed while landing, wherein the minimum approach speed is identified by the retrained DeepQA system, and wherein an auto-assist hydraulic system is required to control a rudder of the physical aircraft if the physical aircraft is flying below the identified minimum approach speed while landing; and
in response to recognizing that the physical aircraft is flying below the identified minimum approach speed while landing, automatically activating, by the retrained DeepQA system, the auto-assist hydraulic system to control a rudder of the physical aircraft while the physical aircraft is landing.

8. The computer program product of claim 7 , wherein the answer key value in the answer key and the answer key value in the candidate passage are exact matches.

9. The computer program product of claim 7 , wherein the answer key value in the answer key and the answer key value in the candidate passage have different values that are within a predefined range.

10. The computer program product of claim 7 , wherein the method further comprises:
analyzing the certain type of question to determine a lexical answer type (LAT) for the certain type of question;
matching the LAT to the candidate passage measurement unit; and
selecting an answer to the certain type of question based on the matching of the LAT to the candidate passage measurement unit.

11. The computer program product of claim 7 , wherein the method further comprises:
assigning an uncertainty value of the answer key measurement unit matching the candidate passage measurement unit; and
generating answers to the certain type of question utilizing terms that have the assigned uncertainty value.

12. The computer program product of claim 7 , wherein the answer key utilizes one or more ground truth measurement units for the answer key measurement unit.

13. The computer program product of claim 7 , wherein the program code is provided as a service in a cloud environment.

14. A computer system comprising one or more processors, one or more computer readable memories, and one or more computer readable non-transitory storage mediums, and program instructions stored on at least one of the one or more computer readable non-trans

Assignees

• IBM

Inventors

• Beller Charles E
• Boxwell Stephen A
• Katz Edward G
• Summers Kristen M

Classifications

• G06F16/3344

  using natural language analysis · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06N5/045 Primary

  Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence · CPC title

• G06N3/08

  Learning methods · CPC title