# US 2021/0065028 A1 · Learning unfamiliar measurement units in a deep question answering system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0065028 A1
- Document ID: US20210065028A1
- Status: Published application
- Kind: A1
- Application number: 16/557,366
- Filed: 2019-08-30
- Published: 2021-03-04
- Earliest claimed: 2019-08-30
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: CHARLES E. BELLER; STEPHEN A. BOXWELL; EDWARD G. KATZ; KRISTEN M. SUMMERS
- Web page: https://patentgrep.com/patent/US20210065028A1

## CPC

- G06F 40/30: Semantic analysis
- G06N 5/045: Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
- G06F 16/3344: {using natural language analysis}
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## 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.

## Claims

### Claim 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;
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;
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; and
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.

### Claim 2 (depends on 1)

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.

### Claim 3 (depends on 1)

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.

### Claim 4 (depends on 1)

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.

### Claim 5 (depends on 1)

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.

### Claim 6 (depends on 1)

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

### Claim 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;
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;
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; and
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.

### Claim 8 (depends on 7)

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.

### Claim 9 (depends on 7)

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.

### Claim 10 (depends on 7)

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.

### Claim 11 (depends on 7)

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.

### Claim 12 (depends on 7)

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.

### Claim 13 (depends on 7)

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

### Claim 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-transitory storage mediums for execution by at least one of the one or more processors via at least one of the one or more computer readable memories, the stored program instructions executed 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;
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;
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; and
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.

### Claim 15 (depends on 14)

The computer system of claim 14, wherein the answer key value in the answer key and the answer key value in the candidate passage are exact matches.

### Claim 16 (depends on 14)

The computer system of claim 14, 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.

### Claim 17 (depends on 14)

The computer system of claim 14, 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.

### Claim 18 (depends on 14)

The computer system of claim 14, 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.

### Claim 19 (depends on 14)

The computer system of claim 14, wherein the answer key utilizes one or more ground truth measurement units for the answer key measurement unit.

### Claim 20 (depends on 14)

The computer system of claim 14, wherein the stored program instructions are provided as a service in a cloud environment.
