Leveraging contextual information in topic coherent question sequences

Patent metadata

Field	Value
Publication number	US-10558689-B2
Application number	US-201715814012-A
Country	US
Kind code	B2
Filing date	Nov 15, 2017
Priority date	Nov 15, 2017
Publication date	Feb 11, 2020
Grant date	Feb 11, 2020

Abstract

A method, computer system, and a computer program product for leveraging coherent question sequences is provided. The present invention may include receiving an initiating question. The present invention may include receiving a subsequent question. The present invention may include determining that the received subsequent question is not a rephrasing of the received initiating question. The present invention may also include determining that the received subsequent question is not beginning a new question topic based on determining that the received subsequent question is not a rephrasing of the received initiating question. The present invention may then include propagating a conversational context based on determining that that received subsequent question is not beginning a new question topic. The present invention may include generating and scoring an answer based on the propagated conversational context. The present invention may lastly include outputting the answer.

First claim

What is claimed is:

1. A computer-implemented method for leveraging coherent question sequences, the method comprising:
receiving an initiating question;
receiving a subsequent question;
determining that the received subsequent question is not a rephrasing of the received initiating question;
determining that the received subsequent question is not beginning a new question topic based on determining that the received subsequent question is not a rephrasing of the received initiating question, by analyzing words in both the received subsequent question and the received initiating question using a hidden variable technique;
propagating a conversational context based on determining that that received subsequent question is not beginning a new question topic;
generating and scoring an answer based on the propagated conversational context; and
outputting the answer.

2. The computer-implemented method of claim 1 , wherein the received initiating question and the received subsequent question are in a spoken form or a written form.

3. The computer-implemented method of claim 1 , wherein contextual information regarding the received initiating question is stored in a conversational context store.

4. The computer-implemented method of claim 1 , wherein determining that the received subsequent question is not the rephrasing of the received initiating question further comprises:
using a synonym detection algorithm to compare the received initiating question to the received subsequent question.

5. The computer-implemented method of claim 1 , wherein determining that the received subsequent question is not beginning the new question topic based on determining that the received subsequent question is not the rephrasing of the received initiating question further comprises:
analyzing words in both the received subsequent question and the received initiating question using a hidden Markov model.

6. The computer-implemented method of claim 1 , wherein propagating the conversational context based on determining that the received subsequent question is not beginning the new question topic comprises utilizing a plurality of information stored within a conversational context store.

7. The computer-implemented method of claim 1 , wherein generating and scoring the answer based on the propagated conversational context further comprises:
combining a plurality of features in a machine learning model.

8. The method of claim 1 , wherein the outputted answer is in a spoken form or a written form.

9. A computer system for leveraging coherent question sequences, 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 an initiating question;
receiving a subsequent question;
determining that the received subsequent question is not a rephrasing of the received initiating question;
determining that the received subsequent question is not beginning a new question topic based on determining that the received subsequent question is not a rephrasing of the received initiating question, by analyzing words in both the received subsequent question and the received initiating question using a hidden variable technique;
propagating a conversational context based on determining that that received subsequent question is not beginning a new question topic;
generating and scoring an answer based on the propagated conversational context; and
outputting the answer.

10. The computer system of claim 9 , wherein the received initiating question and the received subsequent question are in a spoken form or a written form.

11. The computer system of claim 9 , wherein contextual information regarding the received initiating question is stored in a conversational context store.

12. The computer system of claim 9 , wherein determining that the received subsequent question is not the rephrasing of the received initiating question further comprises:
using a synonym detection algorithm to compare the received initiating question to the received subsequent question.

13. The computer system of claim 9 , wherein determining that the received subsequent question is not beginning the new question topic based on determining that the received subsequent question is not the rephrasing of the received initiating question further comprises:
analyzing words in both the received subsequent question and the received initiating question using a hidden Markov model.

14. The computer system of claim 9 , wherein propagating the conversational context based on determining that the received subsequent question is not beginning the new question topic comprises utilizing a plurality of information stored within a conversational context store.

15. The computer system of claim 9 , wherein the outputted answer is in a spoken form or a written form.

16. A computer program product for leveraging coherent question sequences, comprising:
one or more computer-readable storage media and program instructions stored on at least one of the one or more tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising: receiving an initiating question;
receiving a subsequent question;
determining that the received subsequent question is not a rephrasing of the received initiating question;
determining that the received subsequent question is not beginning a new question topic based on determining that the received subsequent question is not a rephrasing of the received initiating question, by analyzing words in both the received subsequent question and the received initiating question using a hidden variable technique;
propagating a conversational context based on determining that that received subsequent question is not beginning a new question topic;
generating and scoring an answer based on the propagated conversational context; and
outputting the answer.

17. The computer program product of claim 16 , wherein the received initiating question and the received subsequent question are in a spoken form or a written form.

18. The computer program product of claim 16 , wherein contextual information regarding the received initiating question is stored in a conversational context store.

19. The computer program product of claim 16 , wherein determining that the received subsequent question is not the rephrasing of the received initiating question further comprises:
using a synonym detection algorithm to compare the received initiating question to the received subsequent question.

20. The computer program product of claim 16 , wherein propagating the conversational context based on determining that the received subsequent question is not beginning the new question topic comprises utilizing a plurality of information stored within a conversational context store.

Assignees

• IBM

Inventors

• Beller Charles E
• Chase Jr Paul J
• Drzewucki Michael
• Katz Edward G
• Phipps Christopher

Classifications

• G06F16/3329 Primary

  Natural language query formulation · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title

• G10L15/01

  Assessment or evaluation of speech recognition systems · CPC title

• G06F16/24522

  Translation of natural language queries to structured queries · CPC title

• G06F16/3334

  Selection or weighting of terms from queries, including natural language queries · CPC title