公开(公告)号：US20160378851A1

公开(公告)日：2016-12-29

申请号：US14749733

申请日：2015-06-25

Applicant: International Business Machines Corporation

Inventor： Erinc Merdivan ,  John A. Riendeau ,  Jadran Sirotkovic ,  Michael D. Whitley ,  Le Zhang

IPC: G06F17/30

Abstract: Mechanisms are provided for processing a knowledge canvassing request. The mechanisms receive a request specifying an entity of interest from an originator of the request and analyze the request to extract a feature of the request. The mechanisms determine whether the request is a targeted natural language question to be answered or a knowledge canvassing request, based on the extracted feature. In response to determining that the request is a knowledge canvassing request, the mechanisms process the request by identifying entities represented in a knowledge graph data structure as being related to the entity of interest. The mechanisms output results of the processing of the request to the originator of the request.

公开(公告)号：US20160171376A1

公开(公告)日：2016-06-16

申请号：US14568209

申请日：2014-12-12

Applicant: International Business Machines Corporation

Inventor： Erinc Merdivan ,  John A. Riendeau ,  Michael D. Whitley ,  Le Zhang

IPC: G06N5/04 ,  G06N7/00

CPC classification number: G06N5/04 ,  G06F16/3329 ,  G06N7/005 ,  G06N20/00

Abstract: An approach is provided in which a knowledge manager identifies a first cohort type and a second cohort type corresponding to an entity included in a question. The knowledge manager determines inferred states to the question by comparing a first set of cohort attributes corresponding to a first cohort type against entity attributes corresponding to the question. In turn, the knowledge manager generates possible answers by comparing the inferred states against a second set of cohort attributes corresponding to a second cohort type.

公开(公告)号：US20160019805A1

公开(公告)日：2016-01-21

申请号：US14872307

申请日：2015-10-01

Applicant: International Business Machines Corporation

Inventor： Corville O. Allen ,  Kyle L. Croutwater ,  Kevin B. Haverlock ,  Michael D. Whitley

IPC: G09B7/00

CPC classification number: G09B7/00 ,  G09B7/02

Abstract: Mechanisms are provided in a data processing system for utilizing algorithms based on categories in a question answering system. The mechanisms capture a history of performance and correctness metrics for identifying efficiency of respective algorithms for finding answers to questions in respective question categories in a question answering system. The mechanisms determine sets of algorithms to use for respective question categories according to efficiency and correctness analysis. The mechanisms determine a question category of a given input question and execute a set of algorithms corresponding to the question category of the given input question that meet an efficiency threshold to contribute to finding a correct answer for the given input question.

Abstract translation: 在用于利用问答系统中的类别的算法的数据处理系统中提供机制。 这些机制捕获了性能和正确性度量的历史，用于识别各种算法的效率，以在问答系统中的各个问题类别中找到问题的答案。 这些机制根据效率和正确性分析确定用于各个问题类别的算法集合。 这些机制确定给定输入问题的问题类别，并执行一组对应于给定输入问题的问题类别的算法，这些算法满足效率阈值，有助于为给定的输入问题找到正确答案。

公开(公告)号：US20150310755A1

公开(公告)日：2015-10-29

申请号：US14262928

申请日：2014-04-28

Applicant: International Business Machines Corporation

Inventor： Kevin B. Haverlock ,  Stephan J. Roorda ,  Michael D. Whitley

IPC: G09B7/02 ,  H04L29/08

CPC classification number: G09B7/02 ,  G09B5/00 ,  H04L67/10

Abstract: An approach is provided for evaluating subject matter experts (SMEs) in a question and answering (QA) system. In the approach, a number of responses are received at the QA system with each of the responses being a response to a common question and each of the responses being received from a SME. One of the responses is selected with the selected response being from one of the SMEs that is being evaluated. The approach evaluates the selected response by comparing the selected response to the responses received from the other SMEs. Based on the evaluation, the approach updates a SME confidence score that corresponds to the selected SME.

Abstract translation: 提供了一种在问答环境（QA）系统中评估主题专家（SMEs）的方法。 在这种方法中，质量保证体系收到了一些答复，每个答复都是对一个共同的问题的答复，每个答复都是从中小企业收到的。 选择的响应之一是所选择的响应来自正在评估的中小型企业之一。 该方法通过将选定的响应与从其他中小企业收到的响应进行比较来评估所选择的响应。 根据评估，该方法更新了对应于所选中小企业的中小企业信心评分。

公开(公告)号：US20140365502A1

公开(公告)日：2014-12-11

申请号：US13914906

申请日：2013-06-11

Applicant: International Business Machines Corporation

Inventor： Peter F. Haggar ,  Dane A. Johnson ,  Stephan J. Roorda ,  Richard L. Stillwell ,  Michael D. Whitley

IPC: G06F17/30

CPC classification number: G06N5/02 ,  G06F17/30684

Abstract: Mechanisms are provided for generating an answer for an input question when the answer is not directly present in a corpus of information. An input question is received from a computing device and analyzed to determine whether the input question is requesting an answer that is calculable. In response to a determination that the input question is requesting an answer that is calculable, one or more constituent data values are retrieved, from a corpus of information, for calculating the requested answer to the input question. A value corresponding to the requested answer is calculated based on the one or more retrieved constituent data values and is then output as the requested answer to the input question.

Abstract translation: 提供了当答案不直接出现在信息语料库中时，为输入问题产生答案的机制。 从计算设备接收输入问题并进行分析，以确定输入问题是否请求可计算的答案。 响应于输入问题要求可计算的答案的确定，从信息语料库检索一个或多个组成数据值，以计算对输入问题的请求答案。 基于一个或多个检索到的构成数据值计算与所请求的答案相对应的值，然后作为所请求的答案输出到输入的问题。

公开(公告)号：US20140297571A1

公开(公告)日：2014-10-02

申请号：US14228830

申请日：2014-03-28

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Bridget B. Beamon ,  Michael D. Whitley ,  Robert L. Yates

IPC: G06N5/04 ,  G06N99/00

CPC classification number: G06N99/005

Abstract: Mechanisms are provided for generating an answer to an input question. An input question is received and a set of candidate answers is generated along with, for each candidate answer in the set of candidate answers, a corresponding selection of one or more selected evidence portions from a corpus of information providing evidence in support of the candidate answer being a correct answer for the input question. The candidate answers are ranked based on an application of a justifying passage model (JPM) to the selected evidence portions for each of the candidate answers in the set of candidate answers. The JPM identifies whether a candidate answer is justified by a selected evidence passage corresponding to the candidate answer. A candidate answer is output as the correct answer for the input question based on the ranking of the candidate answers.

Abstract translation: 提供了用于生成输入问题的答案的机制。 收到一个输入问题，并产生一组候选答案，对于候选答案集合中的每个候选答案，从提供证据的信息语料库中选择一个或多个选定的证据部分来支持候选答案 作为输入问题的正确答案。 基于候选答案集中的每个候选答案的所选证据部分，基于适当通行证模型（JPM）的应用将候选答案排序。 JPM通过与候选答案相对应的选定证据段来确定候选答案是否合理。 基于候选答案的排名，输入候选答案作为输入问题的正确答案。

公开(公告)号：US10769552B2

公开(公告)日：2020-09-08

申请号：US15420228

申请日：2017-01-31

Applicant: International Business Machines Corporation

Inventor： Bridget B. Beamon ,  Michael D. Whitley ,  Robert L. Yates

IPC: G06N20/00 ,  G06F16/61 ,  G06F16/31 ,  G06N5/02

Abstract: Mechanisms are provided for generating an answer to an input question. An input question is received and a set of candidate answers is generated along with, for each candidate answer in the set of candidate answers, a corresponding selection of one or more selected evidence portions from a corpus of information providing evidence in support of the candidate answer being a correct answer for the input question. The candidate answers are ranked based on an application of a justifying passage model (JPM) to the selected evidence portions for each of the candidate answers in the set of candidate answers. The JPM identifies whether a candidate answer is justified by a selected evidence passage corresponding to the candidate answer. A candidate answer is output as the correct answer for the input question based on the ranking of the candidate answers.

公开(公告)号：US10565508B2

公开(公告)日：2020-02-18

申请号：US14568209

申请日：2014-12-12

Applicant: International Business Machines Corporation

Inventor： Erinc Merdivan ,  John A. Riendeau ,  Michael D. Whitley ,  Le Zhang

IPC: G06F17/00 ,  G06F17/20 ,  G06N5/04 ,  G06N7/00 ,  G06N20/00

Abstract: An approach is provided in which a knowledge manager identifies a first cohort type and a second cohort type corresponding to an entity included in a question. The knowledge manager determines inferred states to the question by comparing a first set of cohort attributes corresponding to a first cohort type against entity attributes corresponding to the question. In turn, the knowledge manager generates possible answers by comparing the inferred states against a second set of cohort attributes corresponding to a second cohort type.

公开(公告)号：US20170140304A1

公开(公告)日：2017-05-18

申请号：US15420228

申请日：2017-01-31

Applicant: International Business Machines Corporation

Inventor： Bridget B. Beamon ,  Michael D. Whitley ,  Robert L. Yates

IPC: G06N99/00

Abstract: Mechanisms are provided for generating an answer to an input question. An input question is received and a set of candidate answers is generated along with, for each candidate answer in the set of candidate answers, a corresponding selection of one or more selected evidence portions from a corpus of information providing evidence in support of the candidate answer being a correct answer for the input question. The candidate answers are ranked based on an application of a justifying passage model (JPM) to the selected evidence portions for each of the candidate answers in the set of candidate answers. The JPM identifies whether a candidate answer is justified by a selected evidence passage corresponding to the candidate answer. A candidate answer is output as the correct answer for the input question based on the ranking of the candidate answers.

公开(公告)号：US09621601B2

公开(公告)日：2017-04-11

申请号：US13853261

申请日：2013-03-29

Applicant: International Business Machines Corporation

Inventor： Robert C. Johnson, Jr. ,  Scott M. Lewis ,  Michael D. Whitley ,  Robert L. Yates

IPC: H04L29/06 ,  G06Q10/10

CPC classification number: H04L65/403 ,  G06Q10/101

Abstract: Mechanisms are provided, in association with a question and answer system, for generating answers to an input question. An input question is received and processed to generate at least one query. The at least one query is applied to the corpus to generate a set of candidate answers and corresponding selections of evidence portions of the corpus of information providing evidence in support of the at least one candidate answer being a correct answer for the input question. A graphical user interface (GUI) is output comprising a first GUI sub-section comprising the set of candidate answers, and a second GUI sub-section comprising the evidence portions of the corpus. User input modifying at least one of set of candidate answers or the evidence portions of the corpus of information is received via the GUI and an operation of the data processing system is adjusted based on the user input.