# US 2017/0255609 A1 · Utilizing a dialectical model in a 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 2017/0255609 A1
- Document ID: US20170255609A1
- Status: Published application
- Kind: A1
- Application number: 15/600,754
- Filed: 2017-05-21
- Published: 2017-09-07
- Earliest claimed: 2015-05-27
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Donna K. Byron; Ashok Kumar; Mary D. Swift
- Web page: https://patentgrep.com/patent/US20170255609A1

## CPC

- G06F 40/205: Parsing
- G06F 16/3329: Natural language query formulation
- G06F 40/30: Semantic analysis
- G09B 5/00: Electrically-operated educational appliances (working with questions and answers G09B7/00; simulators G09B9/00; advertising or displaying in general G09F)
- G09B 7/00: Electrically-operated teaching apparatus or devices working with questions and answers (mechanically operated G09B3/00; computing arrangements G06F)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B)

## Abstract

A method, system or computer usable program product for utilizing a dialectical model for providing an answer to a user query including receiving, by a system, a natural language query from a user; applying, by the system, natural language processing (NLP) to the query to generate a first set of NLP structures; generating, by the system, a contrary set of NLP structures which represent an opposite polarity query to the user query; evaluating, by the system, the first set of NLP structures to identify a first set of evidence for candidate answers; evaluating, by the system, the contrary set of NLP structures to identify a second set of evidence for candidate answers; evaluating, by the system, a first set of hypotheses from the first set of NLP structures based on the first set of evidence for candidate answers, and a contrary set of hypotheses from the contrary set of NLP structures based on the second set of evidence for candidate answers, to determine a set of answers to the user query; converting, by the system, the set of answers to natural language; and providing the converted set of answers to the user.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method for utilizing a dialectical model for providing an answer to a user query comprising:
receiving, by a system, a natural language query from a user;
applying, by the system, natural language processing (NLP) to the query to generate a first set of NLP structures;
generating, by the system, a contrary set of NLP structures which represent an opposite polarity query to the user query;
evaluating, by the system, the first set of NLP structures to identify a first set of evidence for candidate answers;
evaluating, by the system, the contrary set of NLP structures to identify a second set of evidence for candidate answers;
evaluating, by the system, a first set of hypotheses from the first set of NLP structures based on the first set of evidence for candidate answers, and a contrary set of hypotheses from the contrary set of NLP structures based on the second set of evidence for candidate answers, to determine a set of answers to the user query;
converting, by the system, the set of answers to natural language; and
providing the converted set of answers to the user.

### Claim 22 (depends on 21)

The method of claim 21, wherein generating the contrary set of NLP structures utilizes domain dependent resources.

### Claim 23 (depends on 21)

The method of claim 21 wherein the contrary set of NLP structures is generated by negating the first set of NLP structures.

### Claim 24 (depends on 21)

The method of claim 21 wherein the contrary set of NLP structures is generated by negating the user query and applying NLP processing to the negated user query.

### Claim 25 (depends on 21)

The method of claim 21 wherein evaluating the first set of NLP structures forms a first set of candidate answers supported by the first set of evidence for candidate answers; and wherein evaluating the contrary set of NLP structures forms a second set of candidate answers supported by the second set of evidence for candidate answers.

### Claim 26 (depends on 25)

The method of claim 25 wherein evaluating the first set of hypotheses includes evaluating the first set of candidate answers supported by the first set of evidence for candidate answers and evaluating contradictory candidate answers supported by the second set of evidence for candidate answers; and wherein evaluating the contrary set of hypotheses includes evaluating the second set of candidate answers supported by the second set of evidence for candidate answers and evaluating contradictory candidate answers supported by the first set of evidence for candidate answers.

### Claim 27 (depends on 21)

The method of claim 21 wherein evaluating the first and contrary set of hypotheses further comprises determining a confidence level for each answer based on the first and second set of evidence for candidate answers supporting each hypothesis.

### Claim 28 (depends on 27)

The method of claim 27 further comprising ranking the set of answers based on the confidence levels for each set of hypotheses.

### Claim 29 (depends on 28)

The method of claim 28 further comprising normalizing the confidence levels for the set of answers.

### Claim 30

A computer program product for utilizing a dialectical model for providing an answer to a user query, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing circuit to cause a device to perform a method comprising:
receiving, by a system, a natural language query from a user;
applying, by the system, natural language processing (NLP) to the query to generate a first set of NLP structures;
generating, by the system, a contrary set of NLP structures which represent an opposite polarity query to the user query;
evaluating, by the system, the first set of NLP structures to identify a first set of evidence for candidate answers;
evaluating, by the system, the contrary set of NLP structures to identify a second set of evidence for candidate answers;
evaluating, by the system, a first set of hypotheses from the first set of NLP structures based on the first set of evidence for candidate answers, and a contrary set of hypotheses from the contrary set of NLP structures based on the second set of evidence for candidate answers, to determine a set of answers to the user query;
converting, by the system, the set of answers to natural language; and
providing the converted set of answers to the user.

### Claim 31 (depends on 30)

The computer program product of claim 30 wherein the contrary set of NLP structures is generated by negating the first set of NLP structures.

### Claim 32 (depends on 30)

The computer program product of claim 30 wherein evaluating the first set of NLP structures forms a first set of candidate answers supported by the first set of evidence for candidate answers; and wherein evaluating the contrary set of NLP structures forms a second set of candidate answers supported by the second set of evidence for candidate answers.

### Claim 33 (depends on 32)

The computer program product of claim 32 wherein evaluating the first set of hypotheses includes evaluating the first set of candidate answers supported by the first set of evidence for candidate answers and evaluating contradictory candidate answers supported by the second set of evidence for candidate answers; and wherein evaluating the contrary set of hypotheses includes evaluating the second set of candidate answers supported by the second set of evidence for candidate answers and evaluating contradictory candidate answers supported by the first set of evidence for candidate answers.

### Claim 34 (depends on 30)

The computer program product of claim 30 wherein evaluating the first and contrary set of hypotheses further comprises determining a confidence level for each answer based on the first and second set of evidence for candidate answers supporting each hypothesis.

### Claim 35 (depends on 34)

The computer program product of claim 34 further comprising ranking the set of answers based on the confidence levels for each set of hypotheses.

### Claim 36

A data processing system for utilizing a dialectical model for providing an answer to a user query, the data processing system comprising:
a processor; and
a memory storing program instructions which when executed by the processor execute steps of:
receiving, by a system, a natural language query from a user;
applying, by the system, natural language processing (NLP) to the query to generate a first set of NLP structures;
generating, by the system, a contrary set of NLP structures which represent an opposite polarity query to the user query;
evaluating, by the system, the first set of NLP structures to identify a first set of evidence for candidate answers;
evaluating, by the system, the contrary set of NLP structures to identify a second set of evidence for candidate answers;
evaluating, by the system, a first set of hypotheses from the first set of NLP structures based on the first set of evidence for candidate answers, and a contrary set of hypotheses from the contrary set of NLP structures based on the second set of evidence for candidate answers, to determine a set of answers to the user query;
converting, by the system, the set of answers to natural language; and
providing the converted set of answers to the user.

### Claim 37 (depends on 36)

The data processing system of claim 36 wherein evaluating the first set of NLP structures forms a first set of candidate answers supported by the first set of evidence for candidate answers; and wherein evaluating the contrary set of NLP structures forms a second set of candidate answers supported by the second set of evidence for candidate answers.

### Claim 38 (depends on 37)

The data processing system of claim 37 wherein evaluating the first set of hypotheses includes evaluating the first set of candidate answers supported by the first set of evidence for candidate answers and evaluating contradictory candidate answers supported by the second set of evidence for candidate answers; and wherein evaluating the contrary set of hypotheses includes evaluating the second set of candidate answers supported by the second set of evidence for candidate answers and evaluating contradictory candidate answers supported by the first set of evidence for candidate answers.

### Claim 39 (depends on 36)

The data processing system of claim 36 wherein evaluating the first and contrary set of hypotheses further comprises determining a confidence level for each answer based on the first and second set of evidence for candidate answers supporting each hypothesis.

### Claim 40 (depends on 39)

The data processing system of claim 39 further comprising ranking the set of answers based on the confidence levels for each set of hypotheses.
