知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

31 records (took 0.018 seconds)

    Schema and cell value aware named entity recognition model for executing natural language queries
    5.
    发明授权
    Schema and cell value aware named entity recognition model for executing natural language queries 有权

    公开(公告)号：US12271698B1

    公开(公告)日：2025-04-08

    申请号：US17537273

    申请日：2021-11-29

    Applicant: Amazon Technologies, Inc.

    Inventor： Jun Wang ,  Sudipta Sengupta ,  Zhiguo Wang ,  Ramesh M Nallapati ,  Bing Xiang

    IPC: G06F40/295 ,  G06F16/2452 ,  G06F16/2458 ,  G06F40/284

    Abstract: A schema and cell value aware Named Entity Recognition (NER) model is used to perform natural language queries. Natural language queries may be received via an interface of a natural language query processing system. A fuzzy search may be performed that allows non-exact matches for column names or cell values of data sets potentially used to answer the natural language query. An NER model that adds a type embedding for an exact match of a column name or cell found in the fuzzy search that corresponds to a span of one or more words may be applied as part of generating the entity prediction for the natural language query. One or more queries to at least one of the data sets may be performed to return a result to the natural language query using the entity prediction generated by the NER machine learning model.

    NEURAL NETWORK TRAINING UNDER MEMORY RESTRAINT
    8.
    发明公开
    NEURAL NETWORK TRAINING UNDER MEMORY RESTRAINT 审中-公开

    公开(公告)号：US20230196113A1

    公开(公告)日：2023-06-22

    申请号：US18112036

    申请日：2023-02-21

    Applicant: Amazon Technologies,Inc

    Inventor： Sudipta Sengupta ,  Randy Renfu Huang ,  Ron Diamant ,  Vignesh Vivekaja

    IPC: G06N3/04

    CPC classification number: G06N3/084 ,  G06N3/04

    Abstract: Methods and systems for training a neural network are provided. In one example, an apparatus comprises a memory that stores instructions; and a hardware processor configured to execute the instructions to: control a neural network processor to perform a loss gradient operation to generate data gradients; after the loss gradient operation completes, control the neural network processor to perform a forward propagation operation to generate intermediate outputs; control the neural network processor to perform a backward propagation operation based on the data gradients and the intermediate outputs to generate weight gradients; receive the weight gradients from the neural network processor; and update weights of a neural network based on the weight gradients.

    Neural network training under memory restraint
    9.
    发明授权
    Neural network training under memory restraint 有权

    公开(公告)号：US11610128B2

    公开(公告)日：2023-03-21

    申请号：US16836421

    申请日：2020-03-31

    Applicant: Amazon Technologies, Inc.

    Inventor： Sudipta Sengupta ,  Randy Renfu Huang ,  Ron Diamant ,  Vignesh Vivekraja

    IPC: G06N3/08 ,  G06N3/084 ,  G06N3/04

    Abstract: Methods and systems for training a neural network are provided. In one example, an apparatus comprises a memory that stores instructions; and a hardware processor configured to execute the instructions to: control a neural network processor to perform a loss gradient operation to generate data gradients; after the loss gradient operation completes, control the neural network processor to perform a forward propagation operation to generate intermediate outputs; control the neural network processor to perform a backward propagation operation based on the data gradients and the intermediate outputs to generate weight gradients; receive the weight gradients from the neural network processor; and update weights of a neural network based on the weight gradients.

Patent Agency Ranking