Document preparation with argumentation support from a deep question answering system

Patent metadata

Field	Value
Publication number	US-10387576-B2
Application number	US-201715827016-A
Country	US
Kind code	B2
Filing date	Nov 30, 2017
Priority date	Nov 30, 2017
Publication date	Aug 20, 2019
Grant date	Aug 20, 2019

Abstract

Dynamic semantic processing of text in a word processing application with engagement of question-answering system. A user provides a text stream to a computer system via an input source. The input text stream includes a first natural language statement. The system determines that the first natural language statement includes a fact-based component expressed in natural language form. The system identifies an initial span and an alternative span of the first natural language component, based on the determining. The system engages a question-answering (QA) system by providing the initial span and the alternative span of the first natural language component to the QA system, and by receiving, in response to the providing, a set of natural language results from the QA system. The system evaluates the initial span and the alternative span of the first natural language component based on the received natural language results.

First claim

What is claimed is:

1. A method for processing user input in a word processing program, comprising:
receiving an input text stream from a user via an input source, the input text stream comprising a first natural language statement;
determining that the first natural language statement comprises a fact-based first natural language component expressed in natural language form;
identifying an initial span and an alternative span of the first natural language component, based on the determining;
engaging a question-answering (QA) system by providing the initial span and the alternative span of the first natural language component to the QA system, and by receiving, in response to the providing, a set of natural language results from the QA system; and
evaluating the initial span and the alternative span of the first natural language component based on the received natural language results.

2. The method of claim 1 , wherein the natural language results comprise a passage, a keyword, or both.

3. The method of claim 2 , wherein each of the passage, the keyword, or both, is associated with a score reflecting how well the passage, the keyword, or both, supports an associated span of text, the associated span of text corresponding to the initial span or the alternative span of the first natural language component.

4. The method of claim 2 , wherein engaging a QA system further comprises receiving a set of scores associated with the passage, a plurality of keyword results, or both.

5. The method of claim 1 , further comprising:
identifying, based on the evaluating, a set of passages and keywords having associated scores corresponding to how well the set of passages and keywords support the initial span and the alternative span of the first natural language component, wherein the associated scores are within a specified range of scores for passages and keywords.

6. The method of claim 1 , further comprising:
outputting, to a user, results of the evaluating via an input/output (I/O) device of a computing device.

7. The method of claim 6 , wherein outputting results of the evaluating via an input/output (I/O) device of the computing device comprises:
highlighting, on a display of the computing device, the initial span of the first natural language component; and
indicating that at least one alternative text span of the first natural language component is associated with a set of passages, keywords, or both, having corresponding scores higher than scores for the initial span of the first natural language component.

8. The method of claim 1 , wherein receiving an input text stream via an input source comprises:
monitoring an input stream of the word processing program based on keyboard input from a user; and
wherein, determining that the first natural language statement comprises a fact-based component comprises
periodically engaging the QA system using, as input to the QA system, a portion of the input stream of the word processing program.

9. The method of claim 1 , wherein evaluating the initial span and the alternative span of the first natural language component based on the received natural language results comprises:
determining which of the initial span and the alternative span of the first natural language component has a higher associated score returned by the QA system.

10. A computer program product for processing user input in a word processing program, the computer program product comprising a non-transitory tangible storage device having program code embodied therewith, the program code executable by a processor of a computer to perform a method, the method comprising:
receiving, by the processor, an input text stream from a user via an input source, the input text stream comprising a first natural language statement;
determining, by the processor, that the first natural language statement comprises a fact-based first natural language component expressed in natural language form;
identifying, by the processor, an initial span and an alternative span of the first natural language component, based on the determining;
engaging, by the processor, a question-answering (QA) system by providing the initial span and the alternative span of the first natural language component to the QA system, and by receiving, in response to the providing, a set of natural language results from the QA system; and
evaluating, by the processor, the initial span and the alternative span of the first natural language component based on the received natural language results.

11. The computer program product of claim 10 , wherein the natural language results comprise a passage, a keyword, or both.

12. The computer program product of claim 11 , wherein each of the passage, the keyword, or both, is associated with a score reflecting how well the passage, the keyword, or both, supports an associated span of text, the associated span of text corresponding to the initial span or the alternative span of the first natural language component.

13. The computer program product of claim 11 , wherein engaging a QA system further comprises receiving a set of scores associated with the passage, a plurality of keyword results, or both.

14. The computer program product of claim 10 , further comprising:
identifying, by the processor, based on the evaluating, a set of passages and keywords having associated scores corresponding to how well the set of passages and keywords support the initial span and the alternative span of the first natural language component, wherein the associated scores are within a specified range of scores for passages and keywords.

15. The computer program product of claim 10 , further comprising:
outputting, by the processor, to a user, results of the evaluating via an input/output (I/O) device of a computing device.

16. The computer program product of claim 15 , wherein outputting results of the evaluating via an input/output (I/O) device of the computing device comprises:
highlighting, by the processor, on a display of the computing device, the initial span of the first natural language component; and
indicating, by the processor, that at least one alternative text span of the first natural language component is associated with a set of passages, keywords, or both, having corresponding scores higher than scores for the initial span of the first natural language component.

17. The computer program product of claim 10 , wherein receiving an input text stream via an input source comprises:
monitoring an input stream of the word processing program based on keyboard input from a user; and
wherein, determining that the first natural language statement comprises a fact-based component comprises
periodically engaging the QA system using, as input to the QA system, a portion of the input stream of the word processing program.

18. A computer system for processing user input in a word processing program, comprising:
one or more computer devices each having one or more processors and one or more tangible storage devices; and
a program embodied on at least one of the one or more storage devices, the program having a plurality of program instructions for execution by the one or more processors, the program instructions comprising instructions for
receiving an input text stream from a user via an input source, the input text stream comprising a first natural language statement;
determining that the first natural language statement comprises a fact-based first natural language component expressed in natural language form;
identifying an initial span and

Assignees

• IBM

Inventors

• Beller Charles E
• Dubyak William G
• Sakthi Palani
• Sheets Robert A
• Summers Kristen M

Classifications

• G06F40/35

  Discourse or dialogue representation · CPC title

• G06F40/289

  Phrasal analysis, e.g. finite state techniques or chunking · CPC title

• G06F40/40 Primary

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F40/268

  Morphological analysis · CPC title