公开(公告)号：US20170091170A1

公开(公告)日：2017-03-30

申请号：US14866066

申请日：2015-09-25

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： BRYAN D. CARDILLO

IPC: G06F17/27

CPC classification number: G06F17/277 ,  G06F17/271 ,  G06F17/274 ,  G06F17/2775 ,  G06F17/2795 ,  G06F17/2881 ,  G06F17/30976

Abstract: A technique for generating a new equivalent phrase for an input phrase includes receiving a first input phrase for natural language expansion. Tokens that correspond to parts of speech are generated for the first input phrase. An original grammar tree is generated using at least some of the tokens. One or more alternate grammar trees are generated that are different from the original grammar tree but substantially equivalent to the original grammar tree. One or more synonyms for at least one of the tokens are generated. Finally, one or more new phrases are generated based on the one or more alternate grammar trees and the one or more synonyms.

公开(公告)号：US20170060838A1

公开(公告)日：2017-03-02

申请号：US15351003

申请日：2016-11-14

Applicant: Intelligent Language, LLC

Inventor： Athena A. Smyros ,  Constantine J. Smyros

IPC: G06F17/27 ,  G01C21/34

CPC classification number: G06F17/278 ,  G01C21/3446 ,  G06F17/274 ,  G06F17/2795 ,  G06Q10/00

Abstract: Textual Geographical Location relates a placename, which is a set of terms, from one to any maximum as defined in an individual language, to a unique point or area (many points) as found on a map or other coordinate system, such as the map of the United States as used in global positioning system (GPS).

Abstract translation: 文本地理位置将一个名称，一组术语从一个单个语言定义的最大值相关联到在地图或其他坐标系上（如地图）中找到的唯一点或区域（许多点） 的美国在全球定位系统（GPS）中使用。

公开(公告)号：US20170052966A1

公开(公告)日：2017-02-23

申请号：US15117850

申请日：2015-02-11

Applicant: Mobilearn Development Ltd.

Inventor： Claes PERSSON

IPC: G06F17/30 ,  G06F17/27 ,  G06F17/24 ,  G06F17/28

CPC classification number: G06F16/9537 ,  G06F16/3337 ,  G06F16/93 ,  G06F16/951 ,  G06F17/24 ,  G06F17/2705 ,  G06F17/2765 ,  G06F17/2795 ,  G06F17/289

Abstract: The invention relate to a computer implemented document retrieval method comprising the steps of: a) allowing a user to input a search term in a first language, b) applying a phonetic algorithm to the search term, so that a phonetic version of the search term is obtained, c) using the output from step b) to perform a search in a plurality of electronic documents in the first language where said search identifies the most relevant document based upon the phonetic version of the search term, d) selecting a translated document that represents the document identified in step c), translated into a second language, and f) returning, to the user, the translated document.

Abstract translation: 本发明涉及一种计算机实现的文档检索方法，包括以下步骤：a）允许用户以第一语言输入搜索词，b）将语音算法应用于搜索词，使得搜索词的语音版本 ，c）使用步骤b）的输出，以所述第一语言的多个电子文档中的搜索为基础，根据搜索词的语音版本来识别最相关的文档，d）选择翻译的文档 其表示在步骤c）中识别的文档，翻译成第二语言，以及f）向用户返回翻译的文档。

公开(公告)号：US09575953B2

公开(公告)日：2017-02-21

申请号：US12310773

申请日：2007-09-06

Applicant: Shinichi Ando ,  Kunihiko Sadamasa ,  Shinichi Doi

Inventor： Shinichi Ando ,  Kunihiko Sadamasa ,  Shinichi Doi

IPC: G06F17/20 ,  G06F17/28 ,  G06F17/27 ,  G06F17/22 ,  G10L13/00 ,  G10L15/26

CPC classification number: G06F17/2735 ,  G06F17/20 ,  G06F17/2223 ,  G06F17/2795 ,  G06F17/2845 ,  G10L13/00 ,  G10L15/26

Abstract: A natural-language processing system includes a registration-candidate storage section that stores therein registration-candidate dictionary data, a judgment means that compares input data against the registration-candidate dictionary data to thereby judge whether or not the input data includes a word corresponding to the registration-candidate dictionary data, an inquiry means that inquires to a user whether or not corresponding dictionary data is to be registered in a dictionary storage section to accept a user's instruction if it is judged that a corresponding word exists, a dictionary registration means that registers the corresponding dictionary data in the dictionary storage section based on the input instruction, and a natural-language processing means that executes a natural-language processing onto the input data by using the dictionary data registered in the dictionary storage section.

Abstract translation: 自然语言处理系统包括：注册候选者存储部分，其存储注册候选词典数据;判断装置，其将输入数据与注册候选词典数据进行比较，从而判断输入数据是否包括与 注册候选词典数据;查询装置，如果判断出存在相应的单词，则向用户询问对应的字典数据是否要被登记在字典存储部分中以接受用户的指令，字典登记表示 基于输入指令，在字典存储部分中登记相应的字典数据;以及自然语言处理装置，其通过使用登记在字典存储部分中的字典数据，对输入数据执行自然语言处理。

公开(公告)号：US20170046425A1

公开(公告)日：2017-02-16

申请号：US15306478

申请日：2015-04-24

Applicant: Semantic Technologies Pty Ltd.

Inventor： Albert Donald Tonkin ,  Dung Xuan Thi Le

IPC: G06F17/30 ,  G06F17/27 ,  G06F17/24

CPC classification number: G06F16/3344 ,  G06F16/367 ,  G06F17/241 ,  G06F17/2705 ,  G06F17/2785 ,  G06F17/2795

Abstract: Apparatus for determining a meaning of an ontology term, the apparatus including an electronic processing device that compares the ontology term to a number of potential ontology term meanings, generates a matching score for the results of each comparison, the matching score being based on a similarity of the ontology term and the potential ontology term meaning and selects a potential ontology term as the ontology term meaning using the matching scores.

Abstract translation: 用于确定本体术语的含义的装置，该装置包括将本体术语与多个潜在的本体术语含义进行比较的电子处理装置，为每个比较的结果生成匹配分数，匹配分数基于相似度 的本体术语和潜在的本体术语意义，并选择潜在的本体术语作为使用匹配分数的本体术语含义。

公开(公告)号：US20160379120A1

公开(公告)日：2016-12-29

申请号：US14859749

申请日：2015-09-21

Applicant: International Business Machines Corporation

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

IPC: G06N5/02 ,  G06F17/28

CPC classification number: G06N5/022 ,  G06F16/3329 ,  G06F16/3344 ,  G06F16/338 ,  G06F16/9024 ,  G06F17/2795

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.

Abstract translation: 提供了处理知识拉票请求的机制。 机制从请求的发起者接收指定感兴趣的实体的请求，并分析请求以提取请求的特征。 这些机制基于提取的特征来确定请求是否是要应答的有针对性的自然语言问题或知识拉票请求。 响应于确定请求是知识拉票请求，机制通过将知识图数据结构中表示的实体识别为与感兴趣的实体相关联来处理该请求。 机制将请求的处理结果输出到请求的发起者。

公开(公告)号：US20160378742A1

公开(公告)日：2016-12-29

申请号：US15257280

申请日：2016-09-06

Applicant: Elsevier B.V.

Inventor： Marius Doornenbal ,  Inga Kohlhof

IPC: G06F17/24 ,  G06F17/27 ,  G06F17/30

CPC classification number: G06F17/241 ,  G06F12/04 ,  G06F12/0886 ,  G06F17/24 ,  G06F17/276 ,  G06F17/2765 ,  G06F17/277 ,  G06F17/2775 ,  G06F17/2785 ,  G06F17/2795 ,  G06F17/28 ,  G06F17/30011 ,  G06F17/30684 ,  G06F17/30864

Abstract: Computer-program products and methods for automatically annotating terms, such as ambiguous terms, in an electronic text document are disclosed. In one embodiment, a method of annotating a text document includes determining, by a computing device, a term of interest within the text document. The method further includes searching a data structure including incongruous term pairs (tx, tt) determined from a controlled vocabulary for the term of interest appearing as a term tt, wherein the term tt is a linguistic head of a term tx of the incongruous term pairs (tx, tt). The method further includes annotating the term of interest with a meaning provided by the controlled vocabulary only if a term tx of the incongruous term pairs (tx, tt) associated with the term of interest in the data structure is not present within a predetermined textual distance of the term of interest in the text document.

Abstract translation: 公开了用于在电子文本文档中自动注释术语（例如模糊术语）的计算机程序产品和方法。 在一个实施例中，注释文本文档的方法包括由计算设备确定文本文档内的感兴趣的术语。 该方法还包括搜索包括从控制词汇确定的不协调术语对（tx，tt）的数据结构，用于出现为术语tt的兴趣词，其中术语tt是不协调术语对的术语tx的语言头部 （tx，tt）。 该方法还包括仅当与数据结构中的感兴趣的术语相关联的不协调术语对（tx，tt）的项tx不存在于预定文本距离内时，由所述受控词汇提供的含义来注释所述感兴趣的术语 在文本文件中感兴趣的术语。

公开(公告)号：US20160371283A1

公开(公告)日：2016-12-22

申请号：US15250708

申请日：2016-08-29

Applicant: International Business Machines Corporation

Inventor： Ananth Chakravarthy ,  Indiver N. Dwivedi

IPC: G06F17/30 ,  G06F17/21 ,  G06F17/27

CPC classification number: G06F16/355 ,  G06F16/2365 ,  G06F16/951 ,  G06F17/218 ,  G06F17/2705 ,  G06F17/2735 ,  G06F17/2795

Abstract: The integrity of an existing tag set associated with a web module is protected by reviewing user-generated proposed additions to the tag set to determine whether the proposed addition is appropriate. An initial test is made to determine whether a proposed addition is trivial; e.g., includes strings of the same character. If the proposed addition is not found to be trivial, it is assessed to determine its relatedness to the existing tag set. The proposed addition is made a part of the tag set only if it is found to be sufficiently related to the existing tag set.

Abstract translation: 与web模块相关联的现有标签集的完整性通过检查用户生成的对标签集的建议添加来确定是否适合所提出的添加来保护。 进行初步测试以确定拟议的加法是否微不足道; 例如包括相同字符的字符串。 如果没有发现提出的添加是微不足道的，则评估其确定与现有标签集的相关性。 只有当发现与现有标签集有足够的关联时，才将该提出的添加部分作为标签集的一部分。

公开(公告)号：US09519871B1

公开(公告)日：2016-12-13

申请号：US14976575

申请日：2015-12-21

Applicant: International Business Machines Corporation

Inventor： Carlos H. Cardonha ,  Stefany Mazon ,  Debora L. Nascimento Ciriaco Pereira ,  Nicole B. Sultanum

IPC: G06F15/18 ,  G06N99/00 ,  G06F17/30 ,  G06N7/00 ,  G06K9/62

CPC classification number: G06N99/005 ,  G06F17/2735 ,  G06F17/274 ,  G06F17/2795 ,  G06F17/30011 ,  G06F17/30684 ,  G06K9/6256 ,  G06N7/005

Abstract: Contextual adaptation of documents automatically replaces words for synonyms that appear within context or topic whey they are being used. A machine learned topic modeling, trained by a set of documents representative of a target user is executed to determine topics of an input document, and to determine words in the document to replace based on determining the relevance of the words to the topics in the documents. An output document is generated based on the input document with the replaced words.

Abstract translation: 文档的上下文自适应自动替换在正在使用的上下文或主题中出现的同义词的单词。 执行机器学习的主题建模，由代表目标用户的一组文档训练，以确定输入文档的主题，并且基于确定单词与文档中的主题的相关性来确定文档中要替换的单词 。 输出文档基于输入文档与替换的单词生成。

公开(公告)号：US20160350359A1

公开(公告)日：2016-12-01

申请号：US14982538

申请日：2015-12-29

Applicant: SAMSUNG SDS CO., LTD.

Inventor： Myung Soo KIM ,  Young Ho Baek ,  Ji Yeon PARK

IPC: G06F17/30 ,  G06F19/00 ,  G06F17/27

CPC classification number: G06F19/326 ,  G06F16/24522 ,  G06F16/24564 ,  G06F16/3344 ,  G06F17/278 ,  G06F17/2795 ,  G06N5/025 ,  G06N20/00

Abstract: Methods and apparatuses for managing rule based on informal data are provided, one of methods comprises, receiving, by a rule management apparatus, informal data representing a rule, analyzing, by the rule management apparatus, the informal data, generating, by the rule management apparatus, formal data that can be processed by a rule engine of the rule management apparatus, using results of the analysis of the informal data, selecting, by the rule management apparatus, one or more items to be corrected for setting the rule from the formal data with reference to a target thesaurus relevant to the rule and processing, by the rule management apparatus, the formal data with the selected items corrected, using the rule engine.

Abstract translation: 提供了基于非正式数据管理规则的方法和装置，方法之一包括：由规则管理装置接收表示规则的非正式数据，由规则管理装置分析非正式数据，由规则管理生成 装置，能够由规则管理装置的规则引擎处理的形式数据，使用非正式数据的分析结果，由规则管理装置选择一个或多个待修正的项目，以从规范设定规则 使用规则引擎参照与规则相关的目标辞典的数据，并由规则管理装置处理使用规则引擎校正所选项目的形式数据。