公开(公告)号：US20160275183A1

公开(公告)日：2016-09-22

申请号：US14858254

申请日：2015-09-18

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Krishna Kummamuru ,  Lakshminarayanan Krishnamurthy ,  Manojkumar Pal

IPC: G06F17/30

CPC classification number: G06F16/337 ,  G06F16/335 ,  G06F16/35 ,  H04W4/08 ,  H04W4/21

Abstract: A method, computer program product, and computer system for identifying data associated with an event. A recommendation is provided to at least the event based upon, at least in part, at least one of a character of the event determined based upon, at least in part, the data associated with the event, and a personality of a real-time crowd at the event determined based upon, at least in part, the data associated with the event.

Abstract translation: 一种用于识别与事件相关联的数据的方法，计算机程序产品和计算机系统。 基于至少部分地基于至少部分地基于与事件相关联的数据确定的事件的角色的至少一个以及实时的个性来至少提供事件的至少一个建议 基于至少部分地基于与事件相关联的数据而确定的事件的人群。

公开(公告)号：US10713438B2

公开(公告)日：2020-07-14

申请号：US15182818

申请日：2016-06-15

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Srinivasa Phani K. Gadde ,  Julius Goth, III

IPC: G06F17/00 ,  G06F17/20 ,  G06F40/284 ,  G06N5/04 ,  G06F40/30 ,  G06F40/289 ,  G06F40/295

Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.

公开(公告)号：US10372819B2

公开(公告)日：2019-08-06

申请号：US14665967

申请日：2015-03-23

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Srinivasa Phani K. Gadde ,  Julius Goth, III

IPC: G06F17/00 ,  G06F17/20 ,  G06F17/27 ,  G06N5/04

Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.

公开(公告)号：US09898170B2

公开(公告)日：2018-02-20

申请号：US14566200

申请日：2014-12-10

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Donna K. Byron ,  Mary D. Swift ,  Timothy Winkler

IPC: G06F17/30 ,  G06F3/0484 ,  H04L29/08

CPC classification number: G06F3/0484 ,  G06F17/30867 ,  G06F17/30905 ,  H04L67/22 ,  H04L67/36

Abstract: An approach is provided for automatically generating user-specific interaction modes for processing question and answers at the information handling system by receiving a question from a user, extracting user context parameters identifying a usage scenario for the user, identifying first input and output presentation modes for the user based on the extracted user context parameters, monitoring user interaction with the system in relation to the question, and adjusting the first input and output presentation modes based on the extracted user context parameters and detected user interaction with the system.

公开(公告)号：US20160300154A1

公开(公告)日：2016-10-13

申请号：US15182818

申请日：2016-06-15

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Srinivasa Phani K. Gadde ,  Julius Goth, III

IPC: G06N7/00 ,  G06F17/27 ,  G06F17/28

Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.

Abstract translation: 一个问答系统，通过执行以下步骤来确定问题是否偏离主题：（i）通过问答系统接收一组文件; （ii）使用命名实体识别识别该组文档中的每个文档的专题子集，其中每个主题子集涉及相应的主题; （iii）使用自然语言处理为每个主题子集分配一组主题得分，其中每个主题分数与在概率语言模型下与相应的主题子集相关联的对应概率相关; 以及（iv）至少部分地基于与所述主题子集对应的主题得分来确定输入到问题应答系统中的问题是否是脱离主题。

公开(公告)号：US20160171983A1

公开(公告)日：2016-06-16

申请号：US14566900

申请日：2014-12-11

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Donna K. Byron ,  Alexander Pikovsky ,  Timothy Winkler

IPC: G10L15/26

CPC classification number: G10L15/26

Abstract: An approach is provided to receive audible speech and convert the received speech to text while the audible speech is being delivered to a user. An annotation candidate is identified in the text and an annotation reference relating to the identified annotation candidate is retrieved and presented to the user.

Abstract translation: 提供了一种方法来接收可听见的语音，并将接收到的语音转换为文本，同时将可听见的语音传送给用户。 在文本中识别注释候选，并且检索与所识别的注释候选相关的注释引用并将其呈现给用户。

公开(公告)号：US20140237355A1

公开(公告)日：2014-08-21

申请号：US14090152

申请日：2013-11-26

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Donna Karen Byron ,  Alexander Pikovsky ,  Edward E. Seabolt

IPC: G06F17/24

CPC classification number: G06F17/28 ,  G06F17/24 ,  G06F17/274 ,  G06F17/2775 ,  G06F17/278 ,  G06F17/2795

Abstract: A method for disambiguation of dependent referring expression in natural language processing is provided in the illustrative embodiments. A portion of a document in a set of document is selected, the portion including a set of dependent referring expression instances. The portion is filtered to identify an instance from a set of dependent referring expression instances by using a linguistic characteristic of the instance, the instance of dependent referring expression referring to a full expression occurring in the set of documents. The full expression is located in one member document in the set of documents by locating where the dependent referring expression is defined to be a stand-in for the full expression. The instance is resolved using the full expression such that information about the full expression is available at a location of the instance.

Abstract translation: 在说明性实施例中提供了在自然语言处理中消除自相关参考表达的歧义的方法。 选择一组文档中的文档的一部分，该部分包括一组依赖的参考表达式实例。 该部分被过滤以通过使用实例的语言特征从一组依赖的参考表达式实例中识别实例，所述依赖引用表达式的实例引用在该组文档中出现的完整表达式。 完整表达式位于文档集中的一个成员文档中，方法是将依赖引用表达式的定义位置定义为完整表达式的备用。 使用完整的表达式解析实例，使得有关完整表达式的信息在实例的位置可用。

公开(公告)号：US09424299B2

公开(公告)日：2016-08-23

申请号：US14641527

申请日：2015-03-09

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Timothy P. Winkler

IPC: G06F17/00 ,  G06F17/30 ,  G06F17/28 ,  G06F17/27

CPC classification number: G06F17/30336 ,  G06F17/278 ,  G06F17/2785 ,  G06F17/2795 ,  G06F17/28 ,  G06F17/30011 ,  G06F17/30616

Abstract: A method, system and computer-usable medium are disclosed for preserving conceptual distance within unstructured documents by characterizing conceptual relationships. Natural language processing is applied to content in a plurality of documents to identify topics and subjects. Analytic analysis is then applied to the identified topics and subjects to identify concepts. The content in each of the plurality of documents is partitioned into a first structured hierarchy, preserving at least one structure in each document inherent in the each document. Access is then provided to the content through a first index based upon utilizing the first structured hierarchy and through a second index utilizing a second structured hierarchy. The conceptual relationship criteria are based upon a directed graph with weights based upon a similarity and a distance based upon concepts.

Abstract translation: 公开了一种方法，系统和计算机可用介质，用于通过表征概念关系来保持非结构化文档内的概念距离。 自然语言处理应用于多个文档中的内容以识别主题和主题。 然后将分析分析应用于识别的主题和主题以识别概念。 多个文档中的每个文档中的内容被划分为第一结构化层次结构，在每个文档中固有的每个文档中保留至少一个结构。 然后基于利用第一结构化层次并通过利用第二结构化层次的第二索引，通过第一索引将访问提供给内容。 概念关系标准基于具有基于基于概念的相似性和距离的权重的有向图。

公开(公告)号：US09424298B2

公开(公告)日：2016-08-23

申请号：US14508200

申请日：2014-10-07

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Timothy P. Winkler

IPC: G06F17/00 ,  G06F17/30 ,  G06F17/28 ,  G06F17/27

CPC classification number: G06F17/30336 ,  G06F17/278 ,  G06F17/2785 ,  G06F17/2795 ,  G06F17/28 ,  G06F17/30011 ,  G06F17/30616

Abstract: A method, system and computer-usable medium are disclosed for preserving conceptual distance within unstructured documents by characterizing conceptual relationships. Natural language processing is applied to content in a plurality of documents to identify topics and subjects. Analytic analysis is then applied to the identified topics and subjects to identify concepts. The content in each of the plurality of documents is partitioned into a first structured hierarchy, preserving at least one structure in each document inherent in the each document. Access is then provided to the content through a first index based upon utilizing the first structured hierarchy and through a second index utilizing a second structured hierarchy. The conceptual relationship criteria are based upon a directed graph with weights based upon a similarity and a distance based upon concepts.

Abstract translation: 公开了一种方法，系统和计算机可用介质，用于通过表征概念关系来保持非结构化文档内的概念距离。 自然语言处理应用于多个文档中的内容以识别主题和主题。 然后将分析分析应用于识别的主题和主题以识别概念。 多个文档中的每个文档中的内容被划分为第一结构化层次结构，在每个文档中固有的每个文档中保留至少一个结构。 然后基于利用第一结构化层次并通过利用第二结构化层次的第二索引，通过第一索引将访问提供给内容。 概念关系标准基于具有基于基于概念的相似性和距离的权重的有向图。

公开(公告)号：US20160098398A1

公开(公告)日：2016-04-07

申请号：US14641527

申请日：2015-03-09

Applicant: International Business Machines Corporation

Inventor： John P. Bufe ,  Timothy P. Winkler

IPC: G06F17/30 ,  G06F17/28

CPC classification number: G06F17/30336 ,  G06F17/278 ,  G06F17/2785 ,  G06F17/2795 ,  G06F17/28 ,  G06F17/30011 ,  G06F17/30616

Abstract: A method, system and computer-usable medium are disclosed for preserving conceptual distance within unstructured documents by characterizing conceptual relationships. Natural language processing is applied to content in a plurality of documents to identify topics and subjects. Analytic analysis is then applied to the identified topics and subjects to identify concepts. The content in each of the plurality of documents is partitioned into a first structured hierarchy, preserving at least one structure in each document inherent in the each document. Access is then provided to the content through a first index based upon utilizing the first structured hierarchy and through a second index utilizing a second structured hierarchy. The conceptual relationship criteria are based upon a directed graph with weights based upon a similarity and a distance based upon concepts.

Abstract translation: 公开了一种方法，系统和计算机可用介质，用于通过表征概念关系来保持非结构化文档内的概念距离。 自然语言处理应用于多个文档中的内容以识别主题和主题。 然后将分析分析应用于识别的主题和主题以识别概念。 多个文档中的每个文档中的内容被划分为第一结构化层次结构，在每个文档中固有的每个文档中保留至少一个结构。 然后基于利用第一结构化层次并通过利用第二结构化层次的第二索引，通过第一索引将访问提供给内容。 概念关系标准基于具有基于基于概念的相似性和距离的权重的有向图。