知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.015 seconds)

    MODEL-BASED SEMANTIC TEXT SEARCHING
    2.
    发明申请
    MODEL-BASED SEMANTIC TEXT SEARCHING 有权

    公开(公告)号：US20210326371A1

    公开(公告)日：2021-10-21

    申请号：US16849885

    申请日：2020-04-15

    Applicant: Adobe Inc.

    Inventor： Trung Bui ,  Yu Gong ,  Tushar Dublish ,  Sasha Spala ,  Sachin Soni ,  Nicholas Miller ,  Joon Kim ,  Franck Dernoncourt ,  Carl Dockhorn ,  Ajinkya Kale

    IPC: G06F16/33 ,  G06N20/00 ,  G06N5/04 ,  G06F40/30

    Abstract: Techniques and systems are described for performing semantic text searches. A semantic text-searching solution uses a machine learning system (such as a deep learning system) to determine associations between the semantic meanings of words. These associations are not limited by the spelling, syntax, grammar, or even definition of words. Instead, the associations can be based on the context in which characters, words, and/or phrases are used in relation to one another. In response to detecting a request to locate text within an electronic document associated with a keyword, the semantic text-searching solution can return strings within the document that have matching and/or related semantic meanings or contexts, in addition to exact matches (e.g., string matches) within the document. The semantic text-searching solution can then output an indication of the matching strings.

    ANSWER SELECTION USING A COMPARE-AGGREGATE MODEL WITH LANGUAGE MODEL AND CONDENSED SIMILARITY INFORMATION FROM LATENT CLUSTERING
    3.
    发明申请
    ANSWER SELECTION USING A COMPARE-AGGREGATE MODEL WITH LANGUAGE MODEL AND CONDENSED SIMILARITY INFORMATION FROM LATENT CLUSTERING 审中-公开

    公开(公告)号：US20200372025A1

    公开(公告)日：2020-11-26

    申请号：US16420764

    申请日：2019-05-23

    Applicant: ADOBE INC.

    Inventor： Seung-hyun Yoon ,  Franck Dernoncourt ,  Trung Huu Bui ,  Doo Soon Kim ,  Carl Iwan Dockhorn ,  Yu Gong

    IPC: G06F16/2452 ,  G06F16/2457 ,  G06F16/28 ,  G06F16/248 ,  G06N20/00

    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for techniques for identifying textual similarity and performing answer selection. A textual-similarity computing model can use a pre-trained language model to generate vector representations of a question and a candidate answer from a target corpus. The target corpus can be clustered into latent topics (or other latent groupings), and probabilities of a question or candidate answer being in each of the latent topics can be calculated and condensed (e.g., downsampled) to improve performance and focus on the most relevant topics. The condensed probabilities can be aggregated and combined with a downstream vector representation of the question (or answer) so the model can use focused topical and other categorical information as auxiliary information in a similarity computation. In training, transfer learning may be applied from a large-scale corpus, and the conventional list-wise approach can be replaced with point-wise learning.

    Answer selection using a compare-aggregate model with language model and condensed similarity information from latent clustering
    4.
    发明授权
    Answer selection using a compare-aggregate model with language model and condensed similarity information from latent clustering 有权

    公开(公告)号：US11113323B2

    公开(公告)日：2021-09-07

    申请号：US16420764

    申请日：2019-05-23

    Applicant: ADOBE INC.

    Inventor： Seung-hyun Yoon ,  Franck Dernoncourt ,  Trung Huu Bui ,  Doo Soon Kim ,  Carl Iwan Dockhorn ,  Yu Gong

    IPC: G06F7/00 ,  G06F16/332 ,  G06N20/00 ,  G06F16/33

    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for techniques for identifying textual similarity and performing answer selection. A textual-similarity computing model can use a pre-trained language model to generate vector representations of a question and a candidate answer from a target corpus. The target corpus can be clustered into latent topics (or other latent groupings), and probabilities of a question or candidate answer being in each of the latent topics can be calculated and condensed (e.g., downsampled) to improve performance and focus on the most relevant topics. The condensed probabilities can be aggregated and combined with a downstream vector representation of the question (or answer) so the model can use focused topical and other categorical information as auxiliary information in a similarity computation. In training, transfer learning may be applied from a large-scale corpus, and the conventional list-wise approach can be replaced with point-wise learning.

    Model-based semantic text searching
    5.
    发明授权
    Model-based semantic text searching 有权

    公开(公告)号：US12130850B2

    公开(公告)日：2024-10-29

    申请号：US18147960

    申请日：2022-12-29

    Applicant: Adobe Inc.

    Inventor： Trung Bui ,  Yu Gong ,  Tushar Dublish ,  Sasha Spala ,  Sachin Soni ,  Nicholas Miller ,  Joon Kim ,  Franck Dernoncourt ,  Carl Dockhorn ,  Ajinkya Kale

    IPC: G06F16/33 ,  G06F40/30 ,  G06N5/04 ,  G06N20/00

    CPC classification number: G06F16/3347 ,  G06F40/30 ,  G06N5/04 ,  G06N20/00

    Abstract: Techniques and systems are described for performing semantic text searches. A semantic text-searching solution uses a machine learning system (such as a deep learning system) to determine associations between the semantic meanings of words. These associations are not limited by the spelling, syntax, grammar, or even definition of words. Instead, the associations can be based on the context in which characters, words, and/or phrases are used in relation to one another. In response to detecting a request to locate text within an electronic document associated with a keyword, the semantic text-searching solution can return strings within the document that have matching and/or related semantic meanings or contexts, in addition to exact matches (e.g., string matches) within the document. The semantic text-searching solution can then output an indication of the matching strings.

    MODEL-BASED SEMANTIC TEXT SEARCHING
    6.
    发明申请
    MODEL-BASED SEMANTIC TEXT SEARCHING 有权

    公开(公告)号：US20230133583A1

    公开(公告)日：2023-05-04

    申请号：US18147960

    申请日：2022-12-29

    Applicant: Adobe Inc.

    Inventor： Trung Bui ,  Yu Gong ,  Tushar Dublish ,  Sasha Spala ,  Sachin Soni ,  Nicholas Miller ,  Joon Kim ,  Franck Dernoncourt ,  Carl Dockhorn ,  Ajinkya Kale

    IPC: G06F16/33 ,  G06N20/00 ,  G06F40/30 ,  G06N5/04

    Abstract: Techniques and systems are described for performing semantic text searches. A semantic text-searching solution uses a machine learning system (such as a deep learning system) to determine associations between the semantic meanings of words. These associations are not limited by the spelling, syntax, grammar, or even definition of words. Instead, the associations can be based on the context in which characters, words, and/or phrases are used in relation to one another. In response to detecting a request to locate text within an electronic document associated with a keyword, the semantic text-searching solution can return strings within the document that have matching and/or related semantic meanings or contexts, in addition to exact matches (e.g., string matches) within the document. The semantic text-searching solution can then output an indication of the matching strings.

    Model-based semantic text searching
    7.
    发明授权
    Model-based semantic text searching 有权

    公开(公告)号：US11567981B2

    公开(公告)日：2023-01-31

    申请号：US16849885

    申请日：2020-04-15

    Applicant: Adobe Inc.

    Inventor： Trung Bui ,  Yu Gong ,  Tushar Dublish ,  Sasha Spala ,  Sachin Soni ,  Nicholas Miller ,  Joon Kim ,  Franck Dernoncourt ,  Carl Dockhorn ,  Ajinkya Kale

    IPC: G06F40/30 ,  G06F16/33 ,  G06N20/00 ,  G06N5/04

    Abstract: Techniques and systems are described for performing semantic text searches. A semantic text-searching solution uses a machine learning system (such as a deep learning system) to determine associations between the semantic meanings of words. These associations are not limited by the spelling, syntax, grammar, or even definition of words. Instead, the associations can be based on the context in which characters, words, and/or phrases are used in relation to one another. In response to detecting a request to locate text within an electronic document associated with a keyword, the semantic text-searching solution can return strings within the document that have matching and/or related semantic meanings or contexts, in addition to exact matches (e.g., string matches) within the document. The semantic text-searching solution can then output an indication of the matching strings.

Patent Agency Ranking