中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

45 records (took 0.025 seconds)

    UTILIZING A DIALECTICAL MODEL IN A QUESTION ANSWERING SYSTEM
    26.
    发明申请
    UTILIZING A DIALECTICAL MODEL IN A QUESTION ANSWERING SYSTEM 审中-公开

    公开(公告)号：US20170255609A1

    公开(公告)日：2017-09-07

    申请号：US15600754

    申请日：2017-05-21

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Donna K. Byron ,  Ashok Kumar ,  Mary D. Swift

    IPC: G06F17/27 ,  G06F17/30 ,  G09B5/00

    CPC classification number: G06F17/2705 ,  G06F17/2785 ,  G06F17/30654 ,  G09B5/00 ,  G09B7/00

    Abstract: A method, system or computer usable program product for utilizing a dialectical model for providing an answer to a user query including receiving, by a system, a natural language query from a user; applying, by the system, natural language processing (NLP) to the query to generate a first set of NLP structures; generating, by the system, a contrary set of NLP structures which represent an opposite polarity query to the user query; evaluating, by the system, the first set of NLP structures to identify a first set of evidence for candidate answers; evaluating, by the system, the contrary set of NLP structures to identify a second set of evidence for candidate answers; evaluating, by the system, a first set of hypotheses from the first set of NLP structures based on the first set of evidence for candidate answers, and a contrary set of hypotheses from the contrary set of NLP structures based on the second set of evidence for candidate answers, to determine a set of answers to the user query; converting, by the system, the set of answers to natural language; and providing the converted set of answers to the user.

    USER INTERFACE FOR A QUERY ANSWERING SYSTEM
    27.
    发明申请
    USER INTERFACE FOR A QUERY ANSWERING SYSTEM 审中-公开
    用户界面查询系统

    公开(公告)号：US20160350406A1

    公开(公告)日：2016-12-01

    申请号：US14722830

    申请日：2015-05-27

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Donna K. Byron ,  Scott H. Isensee ,  Ashok Kumar ,  Mark Marrara ,  Mary D. Swift ,  Cale R. Vardy

    IPC: G06F17/30 ,  G06F17/28

    CPC classification number: G06F17/30684 ,  G06F17/2795 ,  G06F17/3043 ,  G06F17/30654 ,  G06F17/30705 ,  G06F17/30867

    Abstract: A method, system or computer usable program product for utilizing a dialectical model for providing an answer to a user query including applying NLP to the query to generate a first set of NLP structures; generating a contrary set of NLP structures contrary to the user query; evaluating the first set of NLP structures to identify a first set of evidence; evaluating the contrary set of NLP structures to identify a second set of evidence; evaluating a first set of hypotheses from the first set of NLP structures and a contrary set of hypotheses from the contrary set of NLP structures to determine a set of answers to the user query; summarizing the set of answers including indicating derivation thereof; and providing the summarized set of answers to the user.

    Abstract translation: 一种用于利用辩证模型提供对用户查询的答案的方法，系统或计算机可用程序产品，包括将NLP应用于查询以生成第一组NLP结构; 产生与用户查询相反的相反的一组NLP结构; 评估第一组NLP结构以确定第一组证据; 评估相反的一组NLP结构，以确定第二组证据; 从第一组NLP结构评估第一组假设，以及相反的NLP结构集合的相反的一组假设来确定用户查询的一组答案; 总结包括其导出的答案集合; 并向用户提供汇总的答案集。

    Expanding Training Questions through Contextualizing Feature Search
    28.
    发明申请
    Expanding Training Questions through Contextualizing Feature Search 审中-公开
    通过语境化功能搜索扩展培训问题

    公开(公告)号：US20160180242A1

    公开(公告)日：2016-06-23

    申请号：US14573240

    申请日：2014-12-17

    Applicant: International Business Machines Corporation

    Inventor： Donna K. Byron ,  Alexander Pikovsky ,  Mary D. Swift

    IPC: G06N99/00 ,  G06N5/04

    CPC classification number: G06N20/00 ,  G06N5/041

    Abstract: Mechanisms for training a Question and Answer (QA) system are provided. The QA system receives a training question for processing by the QA system and processes the training question to generate an answer to the training question, from a portion of content. The QA system identifies a repeatable pattern of content present in the portion of content in association with the answer to the training question. The QA system applies the repeatable pattern of content to other portions of content to generate at least one additional training question and at least one additional entry in a ground truth data structure to thereby expand a set of training questions and expand the ground truth data structure. The QA system is then trained using the expanded set of training questions and expanded ground truth data structure.

    Abstract translation: 提供了一个用于培训问答（QA）系统的机制。 质量检查系统接收质量检查系统处理的培训问题，并从内容的一部分处理培训问题以产生对培训问题的答案。 QA系统与培训问题的答案相关联地标识存在于内容部分中的可重复的内容模式。 QA系统将可重复的内容模式应用于内容的其他部分以在地面真实数据结构中产生至少一个附加训练问题和至少一个附加条目，从而扩展一组训练问题并扩展基础真实数据结构。 然后使用扩展的一组训练问题和扩大的地面真实数据结构来训练质量检查系统。

    Mitigating voice frequency loss
    29.
    发明授权
    Mitigating voice frequency loss 有权

    公开(公告)号：US11854572B2

    公开(公告)日：2023-12-26

    申请号：US17302981

    申请日：2021-05-18

    Applicant: International Business Machines Corporation

    Inventor： Mary D. Swift ,  Irene Lizeth Manotas Gutiérrez ,  Kelley Anders ,  Jonathan D. Dunne

    IPC: G10L25/18 ,  G10L19/008 ,  G10L25/90 ,  G10L19/02 ,  G10L15/10 ,  G10L15/14

    CPC classification number: G10L25/18 ,  G10L15/10 ,  G10L15/14 ,  G10L19/008 ,  G10L19/0204 ,  G10L25/90

    Abstract: Computer-implemented methods, computer program products, and computer systems for mitigating frequency loss may include one or more processors configured for receiving first audio data corresponding to unobstructed user utterances, receiving second audio data corresponding to first obstructed user utterances, generating a frequency loss (FL) model representing frequency loss between the first audio data and the second audio data, receiving third audio data corresponding to one or more second obstructed user utterances, processing the third audio data using the FL model to generate fourth audio data corresponding to a frequency loss mitigated version of the second obstructed user utterances, and transmitting the fourth audio data to a recipient computing device. The first obstructed user utterances are obstructed by a facemask and the one or more second obstructed user utterances is obstructed by the facemask. The FL model may be executed as an audio plugin in a web conferencing program.

    Real-time optimized translation
    30.
    发明授权
    Real-time optimized translation 有权

    公开(公告)号：US11475226B2

    公开(公告)日：2022-10-18

    申请号：US17026398

    申请日：2020-09-21

    Applicant: International Business Machines Corporation

    Inventor： Mary D. Swift ,  Irene Lizeth Manotas ,  Jonathan D. Dunne

    IPC: G06F40/51 ,  H04L51/046 ,  G06F40/58

    Abstract: In response to determining that a native language of a first user is different from a target language of a message to be transmitted by the first user to a second user, a translation model based on a plurality of language efficacies of the first user is created. An optimal action associated with a translation of the message from the native language to the target language is determined based on the created model and a language efficacy of the first user in the native language. The determined optimal action is performed. The message translation comprising the performed optimal action is transmitted to the second user.

Patent Agency Ranking