知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.012 seconds)

    GENERATING TIME-BASED RECAPS OF DOCUMENTS USING A DEEP LEARNING SEQUENCE TO SEQUENCE MODEL
    1.
    发明申请
    GENERATING TIME-BASED RECAPS OF DOCUMENTS USING A DEEP LEARNING SEQUENCE TO SEQUENCE MODEL 有权

    公开(公告)号：US20220222439A1

    公开(公告)日：2022-07-14

    申请号：US17148125

    申请日：2021-01-13

    Applicant: Adobe, Inc.

    Inventor： Shagun Kush ,  Sachin Soni ,  Nikita Kapoor ,  Carl Iwan Dockhorn ,  Ashish Rawat ,  Ajay Jain ,  Abhishek Jain

    IPC: G06F40/289

    Abstract: Techniques are provided herein for generating improved document summaries that consider the amount of time that has passed since the user last accessed the document. The length of time that has passed since the user has accessed each previous portion of the document is used as a variable to determine how much the summary should focus on each of the previously read sections of the document. When a document is accessed by a user, a relevance score is assigned to content from previously accessed sections of that document, where the relevance score is weighted based on how long ago each of the sections was accessed by the user. Once the various content items of previous sections have been provided relevance scores, selected sentences with the highest relevance scores are fed to a deep learning sequence-to-sequence model is used to build the document summary.

    Answer selection using a compare-aggregate model with language model and condensed similarity information from latent clustering
    2.
    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.

    Generating time-based recaps of documents using a deep learning sequence to sequence model
    4.
    发明授权
    Generating time-based recaps of documents using a deep learning sequence to sequence model 有权

    公开(公告)号：US11604924B2

    公开(公告)日：2023-03-14

    申请号：US17148125

    申请日：2021-01-13

    Applicant: Adobe, Inc.

    Inventor： Shagun Kush ,  Sachin Soni ,  Nikita Kapoor ,  Carl Iwan Dockhorn ,  Ashish Rawat ,  Ajay Jain ,  Abhishek Jain

    IPC: G06F40/106 ,  G06F40/289 ,  G06F40/30

    Abstract: Techniques are provided herein for generating improved document summaries that consider the amount of time that has passed since the user last accessed the document. The length of time that has passed since the user has accessed each previous portion of the document is used as a variable to determine how much the summary should focus on each of the previously read sections of the document. When a document is accessed by a user, a relevance score is assigned to content from previously accessed sections of that document, where the relevance score is weighted based on how long ago each of the sections was accessed by the user. Once the various content items of previous sections have been provided relevance scores, selected sentences with the highest relevance scores are fed to a deep learning sequence-to-sequence model is used to build the document summary.

    ANSWER SELECTION USING A COMPARE-AGGREGATE MODEL WITH LANGUAGE MODEL AND CONDENSED SIMILARITY INFORMATION FROM LATENT CLUSTERING
    5.
    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.

Patent Agency Ranking