公开(公告)号：WO2016033617A3

公开(公告)日：2016-05-26

申请号：PCT/VN2015000010

申请日：2015-08-27

Applicant: NGUYEN DUY THANG

Inventor： NGUYEN DUY THANG

IPC: G06F17/28

CPC classification number: G06F17/2775 ,  G06F17/2872

Abstract: The invention has provided an asynchronous machine translation to standardize and simplify translation process as well as improve translation quality. The invention divides the process of translating from language A to language B into two steps, each of which may be independently developed. Step 1 : translating language A to values stored by multipurpose language data storage method (intermediate data) Step 2: converting intermediate data into any language B, exported data may be text, sound, image, sign... The intermediate data enables to exterminate synonyms. Division of the translation process into two independent steps helps to decrease difficulty of translation between two languages (changing from multiplication to addition) and simultaneously translate multi-languages, independently develop new languages and reduce translation on a device to various devices.

Abstract translation: 本发明提供了异步机器翻译，以标准化和简化翻译过程以及提高翻译质量。 本发明将从语言A翻译成语言B的过程分为两步，每一步都可以独立开发。 步骤1：将语言A翻译成多用途语言数据存储方法存储的值（中间数据）步骤2：将中间数据转换成任何语言B，导出的数据可以是文本，声音，图像，符号...中间数据能够消灭 同义词。 将翻译过程分为两个独立步骤，有助于降低两种语言之间的翻译难度（从乘法到增加），同时翻译多种语言，独立开发新的语言，并将设备上的翻译减少到各种设备。

公开(公告)号：WO2016044321A1

公开(公告)日：2016-03-24

申请号：PCT/US2015/050263

申请日：2015-09-15

Applicant: TANG, Min

Inventor： TANG, Min

IPC: G06F17/27

CPC classification number: G06F17/28 ,  G06F17/277 ,  G06F17/2775 ,  G06F17/2785 ,  G10L15/1815 ,  G10L2015/025

Abstract: The invention relates to a system and method for integrating domain information into state transitions of a Finite State Transducer ("FST") for natural language processing. A system may integrate semantic parsing and information retrieval from an information domain to generate an FST parser that represents the information domain. The FST parser may include a plurality of FST paths, at least one of which may be used to generate a meaning representation from a natural language input. As such, the system may perform domain-based semantic parsing of a natural language input, generating more robust meaning representations using domain information. The system may be applied to a wide range of natural language applications that use natural language input from a user such as, for example, natural language interfaces to computing systems, communication with robots in natural language, personalized digital assistants, question-answer query systems, and/or other natural language processing applications.

Abstract translation: 本发明涉及一种用于将域信息整合到用于自然语言处理的有限状态传感器（“FST”）的状态转换中的系统和方法。 系统可以将来自信息域的语义解析和信息检索整合以生成表示信息域的FST解析器。 FST解析器可以包括多个FST路径，其中的至少一个可以用于从自然语言输入生成意思表示。 因此，系统可以执行基于域的语义解析自然语言输入，使用域信息生成更加鲁棒的含义表示。 该系统可以应用于使用用户的自然语言输入的广泛的自然语言应用，例如对计算系统的自然语言接口，与自然语言的机器人的通信，个性化数字助理，问答回答查询系统 ，和/或其他自然语言处理应用程序。

公开(公告)号：WO2016003508A1

公开(公告)日：2016-01-07

申请号：PCT/US2015/023075

申请日：2015-03-27

Applicant: LINKEDIN CORPORATION

Inventor： AMIN, Mohammad Shafkat ,  YAN, Baoshi ,  BHASIN, Anmol

IPC: G06F17/30

CPC classification number: G06F17/2785 ,  G06F17/24 ,  G06F17/2775 ,  G06F17/28 ,  G06F17/30707 ,  H04L51/12

Abstract: Systems and methods are disclosed for determining whether a short amount of text is irrelevant. A social networking server (204) includes a comment extractor (512) configured to extract one or more comments associated with a selected article. Depending on the number of comments associated with the selected article, the social networking server (204) constructs a native context and/or a transferred context. A native context feature generator (516) is configured to determine a native context feature from the constructed native context and a transferred context feature generator (518) is configured to determine a transferred context feature from the constructed transferred context. The context features (530) may be leveraged by a comment classifier (520) to determine whether a given comment is irrelevant.

Abstract translation: 公开了用于确定短文本是否不相关的系统和方法。 社交网络服务器（204）包括注释提取器（512），其被配置为提取与所选择的文章相关联的一个或多个注释。 根据与所选择的文章相关联的注释的数量，社交网络服务器（204）构造本地上下文和/或传送的上下文。 本地上下文特征生成器（516）被配置为从所构建的本地上下文确定本机上下文特征，并且传送的上下文特征生成器（518）被配置为从所构建的传送上下文中确定传送的上下文特征。 上下文特征（530）可以由注释分类器（520）来利用，以确定给定注释是否不相关。

公开(公告)号：WO2015164209A1

公开(公告)日：2015-10-29

申请号：PCT/US2015/026430

申请日：2015-04-17

Applicant: MAYO FOUNDATION FOR MEDICAL EDUCATION AND RESEARCH

Inventor： WALKER, Randall, C.

IPC: G06F17/24

CPC classification number: G06F17/212 ,  G06F17/211 ,  G06F17/218 ,  G06F17/271 ,  G06F17/274 ,  G06F17/2775 ,  G06F17/2785 ,  G06F19/00 ,  G16H10/60

Abstract: This document provides systems and methods for altering text presentation to increase reading accuracy, efficiency, and retention. This can include identification text specific attributes from machine readable text (through parsing of the text), varying the text presentation in accordance with the attributes, and creating an enhanced visual product for enhancing the reading experience. For example, a computer system can extract attributes such as parts of speech from an input sentence and display that sentence in cascading text segments down and across a display screen. The system can further use domain-specific dictionaries derived from domain-specific texts to identify domain-specific compound noun phrases and verb phrases that require specific linguistic tagging to be usable in other linguistic analysis steps.

Abstract translation: 本文档提供了更改文本显示的系统和方法，以提高读取精度，效率和保留。 这可以包括来自机器可读文本的识别文本特定属性（通过解析文本），根据属性改变文本呈现，以及创建增强的视觉产品以增强阅读体验。 例如，计算机系统可以从输入句子中提取诸如词性之类的属性，并且在逐个显示屏幕之间显示该级别的文本段。 该系统可以进一步使用从特定于领域的文本导出的特定于领域的词典来识别需要特定语言标签以在其他语言分析步骤中可用的特定于领域的复合名词短语和动词短语。

公开(公告)号：WO2014207561A3

公开(公告)日：2015-04-30

申请号：PCT/IB2014001777

申请日：2014-06-27

Applicant: PLOTAGON AB

Inventor： KALDMA JONATHAN HISE ,  LINDSTROM TED ULRIK

IPC: G11B27/031 ,  G06F3/0481 ,  G06F3/0484 ,  G06T13/20 ,  G06T13/40 ,  G06T15/06 ,  G11B27/10 ,  G11B27/34 ,  H04N5/222

CPC classification number: G11B27/031 ,  G06F3/0481 ,  G06F3/04817 ,  G06F3/04847 ,  G06F17/211 ,  G06F17/22 ,  G06F17/2264 ,  G06F17/243 ,  G06F17/2775 ,  G06F17/2872 ,  G06T13/40 ,  G06T2213/08 ,  G06T2213/12 ,  G11B27/34 ,  H04N5/222

Abstract: System, method and apparatuses directed to a paradigm of manuscript generation and manipulation combined with contemporaneous or simultaneous visualization of the text or other media being entered by the creator. Through respective panels or interfaces the creator may manipulate a work or manuscript while visualizing the effects desired.

Abstract translation: 针对原稿生成和操作范例的系统，方法和装置，以及由创作者输入的文本或其他媒体的同时或同时可视化。 通过相应的面板或界面，创作者可以在可视化所需效果的同时操纵作品或手稿。

公开(公告)号：WO2015030796A1

公开(公告)日：2015-03-05

申请号：PCT/US2013/057559

申请日：2013-08-30

Applicant: INTEL CORPORATION ,  DELEEUW, William C.

Inventor： DELEEUW, William C.

IPC: G06F17/30 ,  G06F15/16

CPC classification number: G06F17/2785 ,  G06F17/2775 ,  G06F17/30769 ,  G06F17/30914 ,  G06F17/30976 ,  G10L15/22

Abstract: Technologies for extensible, context-aware natural language interactions include a computing device having a number of context source modules. Context source modules may be developed or installed after deployment of the computing device to a user. Each context source module includes a context capture module, a language model, one or more database query mappings, and may include one or more user interface element mappings. The context capture module interprets, generates, and stores context data. A virtual personal assistant (VPA) of the computing device indexes the language models and generates a semantic representation of a user request that associates each word of the request to a language model. The VPA translates the user request into a database query, and may generate a user interface element for the request. The VPA may execute locally on the computing device or remotely on a cloud server. Other embodiments are described and claimed.

Abstract translation: 用于可扩展，上下文感知的自然语言交互的技术包括具有多个上下文源模块的计算设备。 可以在将计算设备部署到用户之后开发或安装上下文源模块。 每个上下文源模块包括上下文捕获模块，语言模型，一个或多个数据库查询映射，并且可以包括一个或多个用户界面元素映射。 上下文捕获模块解释，生成和存储上下文数据。 计算设备的虚拟个人助理（VPA）对语言模型进行索引，并生成将请求的每个单词与语言模型相关联的用户请求的语义表示。 VPA将用户请求转换为数据库查询，并可以为请求生成用户界面元素。 VPA可以在计算设备上本地执行，也可以在云服务器上远程执行。 描述和要求保护其他实施例。

公开(公告)号：WO2014209810A3

公开(公告)日：2015-02-26

申请号：PCT/US2014043511

申请日：2014-06-20

Applicant: ALIBABA GROUP HOLDING LTD

Inventor： DONG XINGHUA ,  WU KEWEN ,  HUANG PENG ,  LIN FENG

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

CPC classification number: G06F17/2775 ,  G06F17/275 ,  G06F17/2795 ,  G06F17/2827

Abstract: The present disclosure is related to a method and an apparatus of mining synonymous phrases. The method comprises: obtaining, according to a parallel text corpus, a first phrase-alignment relationship from phrases of a current language to phrases of an intermediate language, and a second phrase-alignment relationship from the phrases of the intermediate language to the phrases of the current language; obtaining, for a target phrase of current language, a first set of aligned phrases of the intermediate language that are aligned with the target phrase of the current language based on the first phrase-alignment relationship; obtaining a second set of aligned phrases of the current language that are aligned with selected phrase(s) in the first set of aligned phrases based on the second phrase-alignment relationship; and obtaining synonymous phrases for the target phrase from the second set of aligned phrases.

Abstract translation: 本公开涉及挖掘同义短语的方法和装置。 该方法包括：根据平行文本语料库获得从当前语言的短语到中间语言的短语的第一短语对齐关系，以及从中间语言的短语到短语的第二短语对齐关系 当前语言; 针对当前语言的目标短语获得基于第一短语对准关系与当前语言的目标短语对准的中间语言的第一组对齐短语; 基于第二短语对齐关系，获得与第一组对齐短语中的所选短语对准的当前语言的第二组对齐短语; 并从第二组对齐的短语中获取目标短语的同义词。

公开(公告)号：WO2014209810A2

公开(公告)日：2014-12-31

申请号：PCT/US2014/043511

申请日：2014-06-20

Applicant: ALIBABA GROUP HOLDING LIMITED

Inventor： DONG, Xinghua ,  WU, Kewen ,  HUANG, Peng ,  LIN, Feng

IPC: G06F17/27

CPC classification number: G06F17/2775 ,  G06F17/275 ,  G06F17/2795 ,  G06F17/2827

Abstract: The present disclosure is related to a method and an apparatus of mining synonymous phrases. The method comprises: obtaining, according to a parallel text corpus, a first phrase-alignment relationship from phrases of a current language to phrases of an intermediate language, and a second phrase-alignment relationship from the phrases of the intermediate language to the phrases of the current language; obtaining, for a target phrase of current language, a first set of aligned phrases of the intermediate language that are aligned with the target phrase of the current language based on the first phrase-alignment relationship; obtaining a second set of aligned phrases of the current language that are aligned with selected phrase(s) in the first set of aligned phrases based on the second phrase-alignment relationship; and obtaining synonymous phrases for the target phrase from the second set of aligned phrases.

Abstract translation: 本公开涉及挖掘同义短语的方法和装置。 该方法包括：根据平行文本语料库获得从当前语言的短语到中间语言的短语的第一短语对齐关系，以及从中间语言的短语到短语的第二短语对齐关系 当前语言; 针对当前语言的目标短语获得基于第一短语对齐关系与当前语言的目标短语对准的中间语言的第一组对齐短语; 基于第二短语对齐关系，获得与第一组对齐短语中的所选短语对准的当前语言的第二组对齐短语; 并从第二组对齐的短语中获取目标短语的同义词。

公开(公告)号：WO2014155207A1

公开(公告)日：2014-10-02

申请号：PCT/IB2014/058354

申请日：2014-01-17

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  IBM UNITED KINGDOM LIMITED ,  IBM JAPAN LIMITED

Inventor： ALLEN, Corville, Orain

IPC: G06F17/30

CPC classification number: G06F17/2775 ,  G06F3/04842 ,  G06F17/211 ,  G06F17/218 ,  G06F17/241 ,  G06F17/2765 ,  G06F17/28

Abstract: An approach is provided to detect and hide spoiler information. In the approach, potential spoiler content included user text entries submitted to a collaborative environment are automatically detected. The system inhibits display of the potential spoiler content from the collaborative environment in response to the detection.

Abstract translation: 提供了一种检测和隐藏扰流器信息的方法。 在该方法中，潜在的扰流器内容包括提交给协作环境的用户文本条目被自动检测。 该系统响应于该检测而禁止从协作环境显示潜在扰流器内容。

公开(公告)号：WO2014117549A1

公开(公告)日：2014-08-07

申请号：PCT/CN2013/086152

申请日：2013-10-29

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： LI, Lou ,  CHENG, Qiang ,  RAO, Feng ,  LU, Li ,  ZHANG, Xiang ,  YUE, Shuai ,  CHEN, Bo ,  LU, Duling

IPC: G06F17/27

CPC classification number: G06F17/273 ,  G06F17/2775

Abstract: A computer-implemented method is performed at a device having one or more processors and memory storing programs executed by the one or more processors. The method comprises: selecting a target word in a target sentence; from the target sentence, acquiring a first sequence of words that precede the target word and a second sequence of words that succeed the target word; from a sentence database, searching and acquiring a group of words, each of which separates the first sequence of words from the second sequence of words in a sentence; creating a candidate sentence for each of the candidate words by replacing the target word in the target sentence with each of the candidate words; determining the fittest sentence among the candidate sentences according to a linguistic model; and suggesting the candidate word within the fittest sentence as a correction.

Abstract translation: 在具有一个或多个处理器的设备和由一个或多个处理器执行的存储器存储程序的设备上执行计算机实现的方法。 该方法包括：在目标句子中选择目标词; 从所述目标句子中获取所述目标词之前的第一个单词序列以及继续所述目标单词的第二个单词序列; 从句子数据库中搜索并获取一组单词，每一个单词都将第一个单词序列与一个句子中的第二个单词序列进行分隔; 通过用目标句子中的每个候选词替换目标词来为每个候选词创建候选句子; 根据语言模型确定候选句子中最适合的句子; 并建议适者生词中的候选词作为校正。