知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

17 records (took 0.033 seconds)

    NEURAL MACHINE TRANSLATION SYSTEMS
    1.
    发明申请
    NEURAL MACHINE TRANSLATION SYSTEMS 有权

    公开(公告)号：US20210390271A1

    公开(公告)日：2021-12-16

    申请号：US17459111

    申请日：2021-08-27

    Applicant: Google LLC

    Inventor： Mohammad Norouzi ,  Zhifeng Chen ,  Yonghui Wu ,  Michael Schuster ,  Quoc V. Le

    IPC: G06F40/58 ,  G06F40/44 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural machine translation. The method comprises obtaining a first sequence of words in a source language, generating a modified sequence of words in the source language by inserting a word boundary symbol only at the beginning of each word in the first sequence of words and not at the end of each word, dividing the modified sequence of words into wordpieces using a wordpiece model, generating, from the wordpieces, an input sequence of input tokens for a neural machine translation system; and generating an output sequence of words using the neural machine translation system based on the input sequence of input tokens.

    Implicit bridging of machine learning tasks
    2.
    发明授权
    Implicit bridging of machine learning tasks 有权

    公开(公告)号：US10713593B2

    公开(公告)日：2020-07-14

    申请号：US15394708

    申请日：2016-12-29

    Applicant: Google LLC

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

    IPC: G06N20/00 ,  G06N3/04 ,  G06N3/063 ,  G06F40/44 ,  G06F40/47

    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.

    Implicit bridging of machine learning tasks
    3.
    发明授权
    Implicit bridging of machine learning tasks 有权

    公开(公告)号：US10679148B2

    公开(公告)日：2020-06-09

    申请号：US16402787

    申请日：2019-05-03

    Applicant: Google LLC

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

    IPC: G06N20/00 ,  G06N3/04 ,  G06N3/063 ,  G06F40/44 ,  G06F40/47

    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. An exemplary system applying implicit bridging for machine learning tasks, as described in this specification, trains a machine learning model to perform certain types of machine learning tasks without requiring explicit training data for the certain types of machine learning tasks to be used during training.

    MULTI-TASK LEARNING USING KNOWLEDGE DISTILLATION
    7.
    发明申请
    MULTI-TASK LEARNING USING KNOWLEDGE DISTILLATION 审中-公开

    公开(公告)号：US20190325308A1

    公开(公告)日：2019-10-24

    申请号：US16458506

    申请日：2019-07-01

    Applicant: Google LLC

    Inventor： Junyoung Chung ,  Melvin Jose Johnson Premkumar ,  Michael Schuster ,  Wolfgang Macherey

    IPC: G06N3/08 ,  G06N3/04 ,  G06F17/28

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing multi-task learning. In one method a system obtains a respective set of training data for each of multiple machine learning tasks. For each of the machine learning tasks, the system configures a respective teacher machine learning model to perform the machine learning task by training the teacher machine learning model on the training data. The system trains a single student machine learning model to perform the multiple machine learning tasks using (i) the configured teacher machine learning models, and (ii) the obtained training data.

    REWARD AUGMENTED MODEL TRAINING
    8.
    发明申请
    REWARD AUGMENTED MODEL TRAINING 审中-公开

    公开(公告)号：US20190188566A1

    公开(公告)日：2019-06-20

    申请号：US16328207

    申请日：2017-08-25

    Applicant: GOOGLE LLC

    Inventor： Michael Schuster ,  Samuel Bengio ,  Navdeep Jaitly ,  Zhifeng Chen ,  Dale Eric Schuurmans ,  Mohammad Norouzi ,  Yonghui Wu

    IPC: G06N3/08 ,  G06N20/00

    CPC classification number: G06N3/08 ,  G06N20/00

    Abstract: A method includes obtaining data identifying a machine learning model to be trained to perform a machine learning task, the machine learning model being configured to receive an input example and to process the input example in accordance with current values of a plurality of model parameters to generate a model output for the input example; obtaining initial training data for training the machine learning model, the initial training data comprising a plurality of training examples and, for each training example, a ground truth output that should be generated by the machine learning model by processing the training example; generating modified training data from the initial training data; and training the machine learning model on the modified training data.

    IMPLICIT BRIDGING OF MACHINE LEARNING TASKS
    9.
    发明申请
    IMPLICIT BRIDGING OF MACHINE LEARNING TASKS 有权

    公开(公告)号：US20250021889A1

    公开(公告)日：2025-01-16

    申请号：US18897967

    申请日：2024-09-26

    Applicant: Google LLC

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

    IPC: G06N20/00 ,  G06F40/44 ,  G06F40/47 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063

    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.

Patent Agency Ranking