SYSTEMS AND METHODS FOR HANDLING FORMALITY IN TRANSLATIONS OF TEXT
    1.
    发明申请
    SYSTEMS AND METHODS FOR HANDLING FORMALITY IN TRANSLATIONS OF TEXT 审中-公开
    用于处理文本翻译中的形式的系统和方法

    公开(公告)号:WO2018075190A1

    公开(公告)日:2018-04-26

    申请号:PCT/US2017/052649

    申请日:2017-09-21

    Applicant: GOOGLE LLC

    CPC classification number: G06F17/289 G06F17/2872

    Abstract: A computer-implemented method can include obtaining, by a server computing device, a machine translation model relating sets of source words in a source language to sets of target words in a different target language, each of the sets of source words and target words being labeled with a level of formality with respect to its corresponding language. The method can include receiving, by the server computing device, a request to obtain a translated text representing a translation of a text from the source language to the target language, the request further specifying a desired level of formality for the translated text. The method can include in response to receiving the request, obtaining, by the server computing device, the translated text by translating the text using the machine translation model and the desired level of formality. The method can further include outputting, by the server computing device, the translated text.

    Abstract translation: 计算机实现的方法可以包括由服务器计算设备获得将源语言中的源词汇集合与不同目标语言中的目标词汇集合相关联的机器翻译模型,每个 源词和目标词的集合被标记为关于其相应语言的正式程度。 该方法可以包括由服务器计算设备接收用于获得表示文本从源语言到目标语言的翻译的翻译文本的请求,该请求还指定翻译文本的期望的形式等级。 该方法可以包括:响应于接收到该请求,通过使用机器翻译模型和期望的正式程度来翻译文本,由服务器计算设备获得翻译的文本。 该方法可以进一步包括由服务器计算设备输出翻译的文本。

    METHOD AND SYSTEM FOR GENERATION OF CANDIDATE TRANSLATIONS
    2.
    发明申请
    METHOD AND SYSTEM FOR GENERATION OF CANDIDATE TRANSLATIONS 审中-公开
    用于生成候选翻译的方法和系统

    公开(公告)号:WO2017035382A1

    公开(公告)日:2017-03-02

    申请号:PCT/US2016/048751

    申请日:2016-08-25

    CPC classification number: G06F17/2818 G06F17/2705 G06F17/2785 G06F17/2872

    Abstract: Implementations herein relate to methods and devices for generating candidate translations and for quantizing text as well as words. A method may include generating, by a computing device, pending candidate translations of text to be translated based on predetermined translation rules. The computing device may generate translation probabilities from the text to be translated to the pending candidate translations based on features having impacts on translation probabilities of the pending candidate translations and a predetermined translation probability prediction model. The computing device may then select a predetermined number of pending candidate translations that have the translation probabilities higher than other pending candidate translations in the pending candidate translations to be the candidate translations of the text to be translated. I n implementations, the features having impacts on the translation probabilities may include degrees of semantic similarity between the text to be translated and the candidate translations.

    Abstract translation: 本文中的实现涉及用于生成候选翻译以及用于量化文本以及单词的方法和装置。 一种方法可以包括由计算设备根据预定的翻译规则生成要翻译的文本的待决候选翻译。 计算设备可以基于对未完成的候选翻译的翻译概率的影响的特征和预定的翻译概率预测模型,从要翻译的文本生成转换概率。 然后,计算设备可以选择预定数量的待处理候选翻译,其中翻译概率高于未决候选翻译中的其他未决候选翻译,作为要翻译的文本的候选翻译。 在实现中,对翻译概率的影响的特征可以包括待翻译的文本和候选翻译之间的语义相似度的程度。

    SECOND LANGUAGE ACQUISITION SYSTEMS, METHODS, AND DEVICES
    3.
    发明申请
    SECOND LANGUAGE ACQUISITION SYSTEMS, METHODS, AND DEVICES 审中-公开
    第二语言获取系统,方法和设备

    公开(公告)号:WO2017015220A1

    公开(公告)日:2017-01-26

    申请号:PCT/US2016/042824

    申请日:2016-07-18

    Abstract: Systems, methods, and devices for second language acquisition, using incrementally increasing in-line word and grammar substitution to increase comprehension and retention by presenting new material in an already-understood context. The systems, methods, and devices may be implemented in a range of embodiments, from books to computer systems, and generally use isolated word and phrase substitution with a translated word/phrase in the context of a base language document to convey the meaning of the translated word/phrase to the user by context.

    Abstract translation: 用于第二语言习得的系统,方法和设备,通过逐渐增加的在线单词和语法替代来增加理解和保留,通过在已经了解的上下文中呈现新的材料。 系统,方法和设备可以在从书籍到计算机系统的一系列实施例中实现,并且通常在基本语言文档的上下文中使用具有翻译的单词/短语的隔离的单词和短语替换来传达 通过上下文将用户翻译成单词/短语。

    言語変換装置、言語変換方法、及び言語変換プログラム
    4.
    发明申请
    言語変換装置、言語変換方法、及び言語変換プログラム 审中-公开
    语言转换设备,语言转换方法和语言转换程序

    公开(公告)号:WO2015178042A1

    公开(公告)日:2015-11-26

    申请号:PCT/JP2015/050385

    申请日:2015-01-08

    Inventor: 山口 敬太

    CPC classification number: G06F17/2872 G06F8/41 G06F17/2725 G06F17/274

    Abstract: 自然言語で記述されたビジネスルール文をDRL言語文に自動変換する。言語変換装置10は、自然言語で記述されたビジネスルール文を構文単位でDRL言語文に変換するための構文を定義する構文定義情報30と、ビジネスルール文の要素変数をDRL言語文の要素変数に変換するための変換情報40とを記憶する記憶装置16と、ビジネスルール文と構文定義情報30とを比較することにより、ビジネスルール文の構文を解析し、変換情報40を参照してビジネスルール文をDRL言語文に変換するCPU11とを備える。

    Abstract translation: 本发明将以自然语言编写的业务规则语句自动转换为Drools规则语言(DRL)中的句子。 一种语言转换装置(10)具有存储装置(16),用于存储语法定义信息(30),该语法定义信息定义用于将以自然语言编写的业务规则语句转换为语法单元的DRL语言句子的语法,以及转换信息(40) 用于将业务规则语句的元素变量转换为DRL语言句子的元素变量;以及CPU(11),用于通过比较业务规则句和语法定义信息(30)来分析业务规则句的语法,并将 业务规则语句通过参考转换信息(40)到DRL语言句子。

    SMART CIRCULAR AUDIO BUFFER
    6.
    发明申请
    SMART CIRCULAR AUDIO BUFFER 审中-公开
    智能通信音频缓冲器

    公开(公告)号:WO2015034723A1

    公开(公告)日:2015-03-12

    申请号:PCT/US2014/052925

    申请日:2014-08-27

    Abstract: An audio buffer is used to capture audio in anticipation of a user command to do so. Sensors and processor activity may be monitored, looking for indicia suggesting that the user command may be forthcoming. Upon detecting such indicia, a circular buffer is activated. Audio correction may be applied to the audio stored in the circular buffer. After receiving the user command instructing the device to process or record audio, at least a portion of the audio that was stored in the buffer before the command is combined with audio received after the command. The combined audio may then be processed, transmitted or stored.

    Abstract translation: 使用音频缓冲器来捕获音频,期望用户命令这样做。 可以监控传感器和处理器的活动,寻找表明用户命令可能出现的标记。 在检测到这样的标记时,循环缓冲器被激活。 音频校正可以应用于存储在循环缓冲器中的音频。 在接收到指令设备处理或记录音频的用户命令之后,在命令与命令之后接收的音频组合之后存储在缓冲器中的音频的至少一部分。 然后可以处理,发送或存储组合的音频。

    METHOD AND APPARATUS FOR PROCESSING MESSAGE
    7.
    发明申请
    METHOD AND APPARATUS FOR PROCESSING MESSAGE 审中-公开
    处理信息的方法和装置

    公开(公告)号:WO2015007163A1

    公开(公告)日:2015-01-22

    申请号:PCT/CN2014/081548

    申请日:2014-07-03

    Inventor: LU, Yuyan

    CPC classification number: G06F17/2872 G06F17/275 G06F17/289 H04L51/046

    Abstract: In a method for processing a message, a target language of a user of a mobile terminal is determined. At least one message is displayed when the at least one message is sent by a client in an Instant Messenger (IM) session. When a first operation corresponding to one message of the at least one message is detected, the message corresponding to the first operation is translated into the target language and a translation message is obtained. The translation message is displayed.

    Abstract translation: 在处理消息的方法中,确定移动终端的用户的目标语言。 当Instant Messenger(IM)会话中的客户端发送至少一个消息时,至少显示一条消息。 当检测到与至少一个消息的一个消息相对应的第一操作时,将与第一操作相对应的消息转换成目标语言,并获得翻译消息。 显示翻译消息。

    NATURAL LANGUAGE PROCESSING SYSTEM AND METHOD
    9.
    发明申请
    NATURAL LANGUAGE PROCESSING SYSTEM AND METHOD 审中-公开
    自然语言处理系统和方法

    公开(公告)号:WO2014071330A2

    公开(公告)日:2014-05-08

    申请号:PCT/US2013/068360

    申请日:2013-11-04

    Applicant: FIDO LABS INC.

    Abstract: A natural language processing system is disclosed herein. Embodiments of die NLP system perform hand-written rule-based operations thai do not rely on a trained corpus. Rules can be added or modified at any time to improve accuracy of the system, and to allow the same system to operate on unstructured plain text from many disparate contexts (e.g. articles as well as twitter contexts as wei! as medical articles) without harming accuracy for any one context. Embodiments also include a language decoder (LD) that generates information which is stored in a three-level framework {word, clause, phrase). The LD output is easily leveraged by various software applications to analyze large quantities of text from any source in a mote sophisticated and flexible manner than previously possible. A query language (LDQL) for information extraction from NLP parsers' output is disclosed, with emphasis on on its embodiment, implemented for LD. it is also presented, how to use LDQL for knowledge extraction on the example of application named Knowledge Browser.

    Abstract translation: 本文公开了一种自然语言处理系统。 模具NLP系统的实施例执行不依赖于经过训练的语料库的手写基于规则的操作。 可以随时添加或修改规则,以提高系统的准确性,并允许相同的系统在许多不同的环境(例如,文章以及医疗用品中的微博上下文)中对非结构化纯文本进行操作,而不会损害准确性 对于任何一个上下文 实施例还包括产生存储在三级框架{word,子句,短语)中的信息的语言解码器(LD)。 LD产品很容易被各种软件应用程序所利用,以比以前可能的更精细和灵活的方式从任何来源分析大量的文本。 公开了一种用于NLP解析器输出信息提取的查询语言(LDQL),重点在于其实施方式,用于LD。 还介绍了如何使用LDQL进行知识抽取的应用程序的名称为Knowledge Browser。

    BUILDING AN ONTOLOGY BY TRANSFORMING COMPLEX TRIPLES
    10.
    发明申请
    BUILDING AN ONTOLOGY BY TRANSFORMING COMPLEX TRIPLES 审中-公开
    通过改造复合三重轮构建民族学

    公开(公告)号:WO2013144744A1

    公开(公告)日:2013-10-03

    申请号:PCT/IB2013/051823

    申请日:2013-03-07

    Abstract: An approach for building an ontology is provided. Based on a grammar, extracted complex triples are syntactically transformed to identify core terms. The syntactically transformed complex triples are semantically transformed into simplified triples referring to new terms that conceptualize the core adjectives, adverbs and verbs, and assigning the core terms to respective definitions and keys in a reference ontology, thereby retaining the semantics of the complex triples. Based on a meta-schema of the reference ontology, an enrichment transformation of the simplified triples is performed to create simplified and enriched triples by adding relations derived from a correspondence each term in the simplified triples has with the reference ontology and by adding representations of semantics of reference ontology definitions of the terms. The simplified and enriched triples are stored as an ontology representing knowledge in an application providing the free-form text from which the complex triples were extracted.

    Abstract translation: 提供了一种构建本体的方法。 基于语法,提取的复杂三元组被语法转换以识别核心术语。 语法转换的复合三元组语义转换为简化的三元组,指的是概念化核心形容词,副词和动词的新术语,并将核心术语分配给引用本体中各自的定义和键,从而保留复合三元组的语义。 基于参考本体的元模式,执行简化三元组的富集变换,以通过添加从简化三元组中的每个项与参考本体相关联的关联导出并通过添加语义表示来创建简化和丰富的三元组 的参考本体定义的术语。 简化和丰富的三元组被存储为在应用程序中表示知识的本体,提供了从中提取复杂三元组的自由格式的文本。

Patent Agency Ranking