IP Library Granted Patent US 10,838,993
Granted Patent B2
US 10,838,993 · App. 15/396,977 · Granted Nov 17, 2020

Augment politeness in question answer systems

Inventors: Branimir K. Boguraev (Bedford, NY); Swaminathan Chandrasekaran (Coppell, TX); Bharath Dandala (White Plains, NY); Lakshminarayanan Krishnamurthy (Round Rock, TX)
Assignee: International Business Machines Corporation
G06F16/3344G06F16/90332G06N5/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,838,993
App. No.
15/396,977
Granted
Nov 17, 2020
Kind
B2
Abstract

An approach is provided to receive, at a question answering (QA) system, a question and identify a politeness corresponding to a number of terms corresponding to the question that are included in a corpus of the QA system. The approach identifies the politeness of one or more terms included in each of a set of candidate answers responsive to the question. Finally, the approach scores each of the candidate answers, with the scoring being based, in part, on the politeness identified for each of the terms.

Claims (43)

1. A method implemented by an information handling system that includes a memory and a processor, the method comprising:

classifying data ingested into a question answering (QA) system, wherein the classifying comprises determining a politeness corresponding to one or more terms included in the data, and wherein the classifying results in politeness metadata, including a level of politeness, corresponding to each of the one or more terms;

storing the politeness metadata corresponding to the one or more terms in a corpus utilized by the QA system;

receiving, at the QA system, a question;

identifying one or more question characteristics based on one or more question terms in the received question;

comparing the question characteristics to the politeness metadata stored in the corpus, wherein the comparing results in one or more politeness term characteristics;

augmenting the received question with the politeness term characteristics;

searching the corpus for a plurality of candidate answers to the augmented question;

retrieving the politeness metadata corresponding to one or more terms included in the plurality of candidate answers to the augmented question;

retrieving evolved term data for at least one of the one or more terms included in the plurality of candidate answers, wherein the evolved term data indicates a change in the politeness of the at least one term over time; and

scoring each of the plurality of candidate answers, wherein the scoring is based on the retrieved politeness metadata and the retrieved evolved term data.

2. The method of claim 1 further comprising:

augmenting at least one of the candidate answers with politeness-based data pertaining to one or more terms found in the at least one candidate answer, wherein the politeness-based data includes the politeness metadata and the evolved term data pertaining to the one or more terms.

3. An information handling system comprising:

one or more processors;

one or more data stores accessible by at least one of the processors;

a memory coupled to at least one of the processors; and

a set of computer program instructions stored in the memory and executed by at least one of the processors in order to perform actions of:

classifying data ingested into a question answering (QA) system, wherein the classifying comprises determining a politeness corresponding to one or more terms included in the data, and wherein the classifying results in politeness metadata, including a level of politeness, corresponding to each of the one or more terms;

storing the politeness metadata corresponding to the one or more terms in a corpus utilized by the QA system;

receiving, at the QA system, a question;

identifying one or more question characteristics based on one or more question terms in the received question;

comparing the question characteristics to the politeness metadata stored in the corpus, wherein the comparing results in one or more politeness term characteristics;

augmenting the received question with the politeness term characteristics;

searching the corpus for a plurality of candidate answers to the augmented question;

retrieving the politeness metadata corresponding to one or more terms included in the plurality of candidate answers to the augmented question;

retrieving evolved term data for at least one of the one or more terms included in the plurality of candidate answers, wherein the evolved term data indicates a change in the politeness of the at least one term over time; and

scoring each of the plurality of candidate answers, wherein the scoring is based on the retrieved politeness metadata and the retrieved evolved term data.

4. The information handling system of claim 3 wherein the actions further comprise:

augmenting at least one of the candidate answers with politeness-based data pertaining to one or more terms found in the at least one candidate answer, wherein the politeness-based data includes the politeness metadata and the evolved term data pertaining to the one or more terms.

5. A computer program product stored in a computer readable storage medium, comprising computer program code that, when executed by an information handling system, causes the information handling system to perform actions comprising:

classifying data ingested into a question answering (QA) system, wherein the classifying comprises determining a politeness corresponding to one or more terms included in the data, and wherein the classifying results in politeness metadata, including a level of politeness, corresponding to each of the one or more terms;

storing the politeness metadata corresponding to the one or more terms in a corpus utilized by the QA system;

receiving, at the QA system, a question;

identifying one or more question characteristics based on one or more question terms in the received question;

comparing the question characteristics to the politeness metadata stored in the corpus, wherein the comparing results in one or more politeness term characteristics;

augmenting the received question with the politeness term characteristics;

searching the corpus for a plurality of candidate answers to the augmented question;

retrieving the politeness metadata corresponding to one or more terms included in the plurality of candidate answers to the augmented question;

retrieving evolved term data for at least one of the one or more terms included in the plurality of candidate answers, wherein the evolved term data indicates a change in the politeness of the at least one term over time; and

scoring each of the plurality of candidate answers, wherein the scoring is based on the retrieved politeness metadata and the retrieved evolved term data.

6. The computer program product of claim 5 wherein the actions further comprise:

augmenting at least one of the candidate answers with politeness-based data pertaining to one or more terms found in the at least one candidate answer, wherein the politeness-based data includes the politeness metadata and the evolved term data pertaining to the one or more terms.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 3, 2017
From: BOGURAEV, BRANIMIR K.; CHANDRASEKARAN, SWAMINATHAN; DANDALA, BHARATH; KRISHNAMURTHY, LAKSHMINARAYANAN
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 040824/0500 →
Continuity (1)
Related Publication 20180189630A1 · Jul 5, 2018