公开(公告)号：US20200342182A1

公开(公告)日：2020-10-29

申请号：US16610233

申请日：2019-08-26

Applicant: GOOGLE LLC

Inventor： Melvin Jose Johnson Premkumar ,  Akiko Eriguchi ,  Orhan Firat

IPC: G06F40/58

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.

公开(公告)号：US11373049B2

公开(公告)日：2022-06-28

申请号：US16610233

申请日：2019-08-26

Applicant: Google LLC

Inventor： Melvin Jose Johnson Premkumar ,  Akiko Eriguchi ,  Orhan Firat

IPC: G06F40/58

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.