Adjusting time dependent terminology in a question and answer system

Patent metadata

Field	Value
Publication number	US-10474747-B2
Application number	US-201314107313-A
Country	US
Kind code	B2
Filing date	Dec 16, 2013
Priority date	Dec 16, 2013
Publication date	Nov 12, 2019
Grant date	Nov 12, 2019

Abstract

An approach is provided to adjust time dependent terminology in a question and answering (QA) system. The approach ingests a set of documents to produce a corpus utilized by the QA system. A base time is established and the approach acquires a temporally accurate lexicon of terms that correspond to the base time. A corpus of the QA system is updated according to the lexicon. The QA system answers a question according to the updated corpus.

First claim

What is claimed is:

1. A method, in an information handling system comprising a processor and a memory, of adjusting time dependent terminology in a question and answering (QA) computer system, the method comprising:
ingesting a set of documents to produce a base corpus, the base corpus stored in a computer-readable data store accessible by the QA computer system;
acquiring, by the QA computer system, a plurality of lexicons from one or more feeds from social media;
performing, by the QA computer system, a semantic analysis of one or more terms in the plurality of lexicons, wherein the semantic analysis determines a context and a current usage for the one or more terms;
in response to determining that the current usage of a selected term differs from a standard usage of the selected term, updating a trend value corresponding to the lexicon associated with the selected term;
updating the base corpus of the QA computer system according to the plurality of lexicons, the updating resulting in an updated corpus;
receiving, by the QA computer system, a question from a user device via a communication network; and
answering, by the QA computer system, the question according to the updated corpus, wherein the answering comprises:
searching the updated corpus for a plurality of candidate answers to the question, wherein at least one of the plurality of candidate answers is associated with one of the plurality of lexicons;
scoring the plurality of candidate answers, wherein the scoring for each answer is based partly on the trend value of the lexicon associated with the candidate answer; and
providing to the user device via the communication network one or more of the plurality of candidate answers based on the scoring.

2. The method of claim 1 wherein at least one of the one or more feeds from social media is a live feed.

3. The method of claim 1 further comprising:
wherein at least one of the terms is selected from the group consisting of a slang term, a pop culture term, and an event-related term.

4. The method of claim 1 , wherein updating the trend value corresponding to the lexicon associated with the selected term further comprises:
increasing the trend value corresponding to the lexicon in response to an increase in a time-based usage amount of the selected term; and
decreasing the trend value corresponding to the lexicon in response to a decrease in the time-based usage amount of the selected term.

5. An information handling system comprising:
one or more processors;
a memory coupled to at least one of the processors;
a display; and
a set of instructions stored in the memory and executed by at least one of the processors to adjust time dependent terminology in a question and answering (QA) computer system, wherein the set of instructions perform actions of:
ingesting a set of documents to produce a base corpus, the base corpus stored in a computer-readable data store accessible by the QA system;
acquiring by the QA computer system, a plurality of lexicons from one or more feeds from social media;
performing, by the QA computer system, a semantic analysis of one or more terms in the plurality of lexicons, wherein the semantic analysis determines a context and a current usage for the one or more terms;
in response to determining that the current usage of a selected term differs from a standard usage of the selected term, updating a trend value corresponding to the lexicon associated with the selected term;
updating the corpus of the QA computer system according to the plurality of lexicons, the updating resulting in an updated corpus;
receiving, by the QA computer system, a question from a user device via a communication network; and

answering, by the QA computer system, the question according to the updated corpus, wherein the answering comprises:
searching the updated corpus for a plurality of candidate answers to the question, wherein at least one of the plurality of candidate answers is associated with one of the plurality of lexicons;
scoring the plurality of candidate answers, wherein the scoring for each answer is based partly on the trend value of the lexicon associated with the candidate answer; and
providing to the user device via the communication network one or more of the plurality of candidate answers based on the scoring.

6. The information handling system of claim 5 wherein at least one of the one or more feeds from social media is a live feed.

7. The information handling system of claim 5 further comprising:
wherein at least one of the terms is selected from the group consisting of a slang term, a pop culture term, and an event-related term.

8. The information handling system of claim 5 , wherein updating the trend value corresponding to the lexicon associated with the selected term further comprises:
increasing the trend value corresponding to the lexicon in response to an increase in a time-based usage amount of the selected term; and
decreasing the trend value corresponding to the lexicon in response to a decrease in the time-based usage amount of the selected term.

9. A non-transitory computer readable storage medium, comprising computer instructions stored thereon that, when executed by an information handling system, causes the information handling system to adjust time dependent terminology in a question and answering (QA) computer system by performing actions comprising:
ingesting a set of documents to produce a base corpus, the base corpus stored in a computer-readable data store accessible by the QA computer system;
acquiring, by the QA computer system, a plurality of lexicons from one or more feeds from social media;
performing, by the QA computer system, a semantic analysis of one or more terms in the plurality of lexicons, wherein the semantic analysis determines a context and a current usage for the one or more terms;
in response to determining that the current usage of a selected term differs from a standard usage of the selected term, updating a trend value corresponding to the lexicon associated with the selected term;
updating the base corpus of the QA computer system according to the plurality of lexicons, the updating resulting in an updated corpus;
receiving, by the QA computer system, a question from a user device via a communication network; and
answering, by the QA computer system, the question according to the updated corpus, wherein the answering comprises:
searching the updated corpus for a plurality of candidate answers to the question, wherein at least one of the plurality of candidate answers is associated with one of the plurality of lexicons;
scoring the plurality of candidate answers, wherein the scoring for each answer is based partly on the trend value of the lexicon associated with the candidate answer; and
providing to the user device via the communication network one or more of the plurality of candidate answers based on the scoring.

10. The non-transitory computer readable storage medium of claim 9 wherein at least one of the one or more feeds from social media is a live feed.

11. The non-transitory computer readable storage medium of claim 9 further comprising:
wherein at least one of the terms is selected from the group consisting of a slang term, a pop culture term, and an event-related term.

12. The non-transitory computer readable storage medium of claim 9 , wherein updating the trend value corresponding to the lexicon associated with the selected term further comprises:
increasing the trend value corresponding to the lexicon in response to an increase in a time-based usage amount of the selected term; and
decreasing the trend value corresponding to the

Assignees

• IBM

Inventors

• Jamrog Daniel M
• Lavoie Jason D
• Orrick Nicholas W
• Witherspoon Kristin A

Classifications

• G06F40/205 Primary

  Parsing · CPC title

• G06F17/2705 Primary

  Physics · mapped topic