Invention Grant
- Patent Title: Neural machine translation systems
-
Application No.: US16336870Application Date: 2017-09-25
-
Publication No.: US11113480B2Publication Date: 2021-09-07
- Inventor: Mohammad Norouzi , Zhifeng Chen , Yonghui Wu , Michael Schuster , Quoc V. Le
- Applicant: GOOGLE LLC
- Applicant Address: US CA Mountain View
- Assignee: GOOGLE LLC
- Current Assignee: GOOGLE LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- International Application: PCT/US2017/053267 WO 20170925
- International Announcement: WO2018/058046 WO 20180329
- Main IPC: G06F40/58
- IPC: G06F40/58 ; G06F40/44 ; G06N3/04

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural machine translation. One of the systems includes an encoder neural network comprising: an input forward long short-term memory (LSTM) layer configured to process each input token in the input sequence in a forward order to generate a respective forward representation of each input token, an input backward LSTM layer configured to process each input token in a backward order to generate a respective backward representation of each input token and a plurality of hidden LSTM layers configured to process a respective combined representation of each of the input tokens in the forward order to generate a respective encoded representation of each of the input tokens; and a decoder subsystem configured to receive the respective encoded representations and to process the encoded representations to generate an output sequence.
Public/Granted literature
- US20200034435A1 NEURAL MACHINE TRANSLATION SYSTEMS Public/Granted day:2020-01-30
Information query