Patents by Inventor Akiko Eriguchi

Akiko Eriguchi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Cross-lingual classification using multilingual neural machine translation
    Patent number: 11373049
    Abstract: Training and/or using a multilingual classification neural network model to perform a natural language processing classification task, where the model reuses an encoder portion of a multilingual neural machine translation model. In a variety of implementations, a client device can generate a natural language data stream from a spoken input from a user. The natural language data stream can be applied as input to an encoder portion of the multilingual classification model. The output generated by the encoder portion can be applied as input to a classifier portion of the multilingual classification model. The classifier portion can generate a predicted classification label of the natural language data stream. In many implementations, an output can be generated based on the predicted classification label, and a client device can present the output.
    Type: Grant
    Filed: August 26, 2019
    Date of Patent: June 28, 2022
    Assignee: GOOGLE LLC
    Inventors: Melvin Jose Johnson Premkumar, Akiko Eriguchi, Orhan Firat
  • CROSS-LINGUAL CLASSIFICATION USING MULTILINGUAL NEURAL MACHINE TRANSLATION
    Publication number: 20200342182
    Abstract: Training and/or using a multilingual classification neural network model to perform a natural language processing classification task, where the model reuses an encoder portion of a multilingual neural machine translation model. In a variety of implementations, a client device can generate a natural language data stream from a spoken input from a user. The natural language data stream can be applied as input to an encoder portion of the multilingual classification model. The output generated by the encoder portion can be applied as input to a classifier portion of the multilingual classification model. The classifier portion can generate a predicted classification label of the natural language data stream. In many implementations, an output can be generated based on the predicted classification label, and a client device can present the output.
    Type: Application
    Filed: August 26, 2019
    Publication date: October 29, 2020
    Inventors: Melvin Jose Johnson Premkumar, Akiko Eriguchi, Orhan Firat