中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.015 seconds)

    MACHINE LEARNING SYSTEM TO SCORE ALT-TEXT IN IMAGE DATA
    1.
    发明申请
    MACHINE LEARNING SYSTEM TO SCORE ALT-TEXT IN IMAGE DATA 有权

    公开(公告)号：US20210073617A1

    公开(公告)日：2021-03-11

    申请号：US16567277

    申请日：2019-09-11

    Applicant: Amazon Technologies, Inc.

    Inventor： Loris Bazzani ,  Maksim Lapin ,  Felix Hieber ,  Tobias Domhan

    IPC: G06N3/04 ,  G06N3/10 ,  G06N20/00 ,  G06K9/62 ,  G06F17/18 ,  G06F17/16 ,  G06F17/21

    Abstract: Techniques are generally described for automatic scoring of alt-text for image data. In various examples, first image data and first text data describing the first image data may be received. A feature representation of the first image data may be determined using an encoder machine learning model. A hidden state representation may be determined using a decoder machine learning model based on the feature representation and a first word of the first text data. In some examples, a first score may be determined using the hidden state representation. The first score may include an indication of a descriptive capability of the first text data with respect to the first image data.

    Machine learning system to score alt-text in image data
    3.
    发明授权
    Machine learning system to score alt-text in image data 有权

    公开(公告)号：US11361212B2

    公开(公告)日：2022-06-14

    申请号：US16567277

    申请日：2019-09-11

    Applicant: Amazon Technologies, Inc.

    Inventor： Loris Bazzani ,  Maksim Lapin ,  Felix Hieber ,  Tobias Domhan

    IPC: G06N3/04 ,  G06N20/00 ,  G06F40/117 ,  G06F17/16 ,  G06F17/18 ,  G06K9/62 ,  G06N3/10

    Abstract: Techniques are generally described for automatic scoring of alt-text for image data. In various examples, first image data and first text data describing the first image data may be received. A feature representation of the first image data may be determined using an encoder machine learning model. A hidden state representation may be determined using a decoder machine learning model based on the feature representation and a first word of the first text data. In some examples, a first score may be determined using the hidden state representation. The first score may include an indication of a descriptive capability of the first text data with respect to the first image data.

    Separating translation correction post-edits from content improvement post-edits in machine translated content
    4.
    发明授权
    Separating translation correction post-edits from content improvement post-edits in machine translated content 有权

    公开(公告)号：US10248651B1

    公开(公告)日：2019-04-02

    申请号：US15360286

    申请日：2016-11-23

    Applicant: Amazon Technologies, Inc.

    Inventor： Hagen Fuerstenau ,  Felix Hieber

    IPC: G06F17/28 ,  G06F17/24

    Abstract: Machine learning models can determine whether post-edits to machine translated content are corrective post-edits, which are edits made to correct translation errors caused during machine translation, or content improvement post-edits, which are post-edits that have been made to improve source language content. The corrective post-edits can be utilized to generate or modify labels for strings utilized to train a translation quality estimation system. The content improvement post-edits can be utilized to improve the quality of source content prior to providing the source content to the machine translation system for translation.

Patent Agency Ranking