Invention Application
- Patent Title: MACHINE TRANSLATION USING NEURAL NETWORK MODELS
-
Application No.: US17459041Application Date: 2021-08-27
-
Publication No.: US20220083746A1Publication Date: 2022-03-17
- Inventor: Zhifeng Chen , Macduff Richard Hughes , Yonghui Wu , Michael Schuster , Xu Chen , Llion Owen Jones , Niki J. Parmar , George Foster , Orhan Firat , Ankur Bapna , Wolfgang Macherey , Melvin Jose Johnson Premkumar
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Main IPC: G06F40/58
- IPC: G06F40/58 ; G06N3/08

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural network comprising a plurality of bidirectional recurrent neural network layers. The encoding vectors are processed using a multi-headed attention module configured to generate multiple attention context vectors for each encoding vector. A decoder neural network generates a sequence of decoder output vectors using the attention context vectors. The decoder output vectors can represent distributions over various language elements of the second language, allowing a translation of the text into the second language to be determined based on the sequence of decoder output vectors.
Public/Granted literature
- US11809834B2 Machine translation using neural network models Public/Granted day:2023-11-07
Information query