中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

10 records (took 0.032 seconds)

    Large language models in machine translation
    3.
    发明授权
    Large language models in machine translation 有权
    机器翻译中的大语言模型

    公开(公告)号：US08812291B2

    公开(公告)日：2014-08-19

    申请号：US13709125

    申请日：2012-12-10

    Applicant: Google Inc.

    Inventor： Thorsten Brants ,  Ashok C. Popat ,  Peng Xu ,  Franz J. Och ,  Jeffrey Dean

    IPC: G06F17/28

    CPC classification number: G06F17/2818 ,  G06F17/2827 ,  G06F17/2845

    Abstract: Systems, methods, and computer program products for machine translation are provided. In some implementations a system is provided. The system includes a language model including a collection of n-grams from a corpus, each n-gram having a corresponding relative frequency in the corpus and an order n corresponding to a number of tokens in the n-gram, each n-gram corresponding to a backoff n-gram having an order of n−1 and a collection of backoff scores, each backoff score associated with an n-gram, the backoff score determined as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.

    Abstract translation: 提供了用于机器翻译的系统，方法和计算机程序产品。 在一些实现中，提供了一种系统。 该系统包括语言模型，其包括来自语料库的n-gram的集合，每个n-gram在语料库中具有对应的相对频率，并且n阶对应于n-gram中的令牌数量，每个n-gram对应 到具有n-1级的退避n-gram和回退分数的集合，与n-gram相关联的每个回退分数，作为退避因子的函数确定的退避分数和相应退避n的相对频率 -gram在语料库中。

    Semantic unit recognition
    4.
    发明授权
    Semantic unit recognition 有权
    语义单位识别

    公开(公告)号：US08626492B1

    公开(公告)日：2014-01-07

    申请号：US13739648

    申请日：2013-01-11

    Applicant: Google Inc.

    Inventor： Thorsten Brants ,  Jay Ponte

    IPC: G06F17/27

    CPC classification number: G06F17/277 ,  G06F17/2785

    Abstract: A semantic locator determines whether input sequences form semantically meaningful units. The semantic locator includes a coherence component that calculates a coherence of the terms in the sequence and a variation component that calculates the variation in terms that surround the sequence. A heuristics component may additionally refine results of the coherence component and the variation component. A decision component may make the determination of whether the sequence is a semantic unit based on the results of the coherence component, variation component, and heuristics component.

    Abstract translation: 语义定位器确定输入序列是否形成语义有意义的单元。 语义定位器包括一个相干分量，该相干分量计算序列中的项的相干性，以及计算该序列周围的变化的变化分量。 启发式组件可以另外改进相干分量和变化分量的结果。 决策组件可以基于相干分量，变化分量和启发式分量的结果来确定序列是否是语义单元。

    LARGE LANGUAGE MODELS IN MACHINE TRANSLATION
    5.
    发明申请
    LARGE LANGUAGE MODELS IN MACHINE TRANSLATION 有权
    机器翻译中的大量语言模型

    公开(公告)号：US20130346059A1

    公开(公告)日：2013-12-26

    申请号：US13709125

    申请日：2012-12-10

    Applicant: GOOGLE INC.

    Inventor： Thorsten Brants ,  Ashok C. Popat ,  Peng Xu ,  Franz J. Och ,  Jeffrey Dean

    IPC: G06F17/28

    CPC classification number: G06F17/2818 ,  G06F17/2827 ,  G06F17/2845

    Abstract: Systems, methods, and computer program products for machine translation are provided. In some implementations a system is provided. The system includes a language model including a collection of n-grams from a corpus, each n-gram having a corresponding relative frequency in the corpus and an order n corresponding to a number of tokens in the n-gram, each n-gram corresponding to a backoff n-gram having an order of n−1 and a collection of backoff scores, each backoff score associated with an n-gram, the backoff score determined as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.

    Abstract translation: 提供了用于机器翻译的系统，方法和计算机程序产品。 在一些实现中，提供了一种系统。 该系统包括语言模型，其包括来自语料库的n-gram的集合，每个n-gram在语料库中具有对应的相对频率，并且n阶对应于n-gram中的令牌数量，每个n-gram对应 到具有n-1级的退避n-gram和回退分数的集合，与n-gram相关联的每个回退分数，作为退避因子的函数确定的退避分数和相应退避n的相对频率 -gram在语料库中。

    IMPLICIT BRIDGING OF MACHINE LEARNING TASKS
    6.
    发明申请
    IMPLICIT BRIDGING OF MACHINE LEARNING TASKS 审中-公开

    公开(公告)号：US20180129972A1

    公开(公告)日：2018-05-10

    申请号：US15394708

    申请日：2016-12-29

    Applicant: Google Inc.

    Inventor： Zhifeng Chen ,  Michael Schuster ,  Melvin Jose Johnson Premkumar ,  Yonghui Wu ,  Quoc V. Le ,  Maxim Krikun ,  Thorsten Brants

    IPC: G06N99/00 ,  G06F17/28

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.

    Context-based filtering of search results
    7.
    发明授权
    Context-based filtering of search results 有权

    公开(公告)号：US09779139B1

    公开(公告)日：2017-10-03

    申请号：US15070769

    申请日：2016-03-15

    Applicant: Google Inc.

    Inventor： Sarveshwar Duddu ,  Kuntal Loya ,  Minh Tue Vo Thanh ,  Thorsten Brants

    IPC: G06F17/30

    CPC classification number: G06F17/30528 ,  G06F17/3053 ,  G06F17/30598 ,  G06F17/30707 ,  G06F17/30867

    Abstract: A server is configured to receive, from a client, a query and context information associated with a document; obtain search results, based on the query, that identify documents relevant to the query; analyze the context information to identify content; generate first scores for a hierarchy of topics, that correspond to measures of relevance of the topics to the content; select a topic that is most relevant to the context information when the topic is associated with a greatest first score; generate second scores for the search results that correspond to measures of relevance, of the search results, to the topic; select one or more of the search results as being most relevant to the topic when the search results are associated with one or more greatest second scores; generate a search result document that includes the selected search results; and send, to a client, the search result document.

Patent Agency Ranking