公开(公告)号：US20190188268A1

公开(公告)日：2019-06-20

申请号：US16193387

申请日：2018-11-16

Applicant: Google LLC

Inventor： Quoc V. Le ,  Minh-Thang Luong ,  Ilya Sutskever ,  Oriol Vinyals ,  Wojciech Zaremba

IPC: G06F17/28 ,  G06F17/27 ,  G10L15/16 ,  G06N3/04 ,  G06F7/10 ,  G06F7/02 ,  G10L15/02

CPC classification number: G06F17/2881 ,  G06F7/023 ,  G06F7/10 ,  G06F17/2735 ,  G06F17/2818 ,  G06F17/2827 ,  G06N3/0445 ,  G06N3/0454 ,  G10L15/02 ,  G10L15/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural translation systems with rare word processing. One of the methods is a method training a neural network translation system to track the source in source sentences of unknown words in target sentences, in a source language and a target language, respectively and includes deriving alignment data from a parallel corpus, the alignment data identifying, in each pair of source and target language sentences in the parallel corpus, aligned source and target words; annotating the sentences in the parallel corpus according to the alignment data and a rare word model to generate a training dataset of paired source and target language sentences; and training a neural network translation model on the training dataset.

公开(公告)号：US10936828B2

公开(公告)日：2021-03-02

申请号：US16193387

申请日：2018-11-16

Applicant: Google LLC

Inventor： Quoc V. Le ,  Minh-Thang Luong ,  Ilya Sutskever ,  Oriol Vinyals ,  Wojciech Zaremba

IPC: G06F17/28 ,  G06F40/56 ,  G06N3/04 ,  G06F40/44 ,  G06F40/45 ,  G06F40/242 ,  G06F7/02 ,  G06F7/10 ,  G10L15/02 ,  G10L15/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural translation systems with rare word processing. One of the methods is a method training a neural network translation system to track the source in source sentences of unknown words in target sentences, in a source language and a target language, respectively and includes deriving alignment data from a parallel corpus, the alignment data identifying, in each pair of source and target language sentences in the parallel corpus, aligned source and target words; annotating the sentences in the parallel corpus according to the alignment data and a rare word model to generate a training dataset of paired source and target language sentences; and training a neural network translation model on the training dataset.

公开(公告)号：US10133739B2

公开(公告)日：2018-11-20

申请号：US14921925

申请日：2015-10-23

Applicant: GOOGLE LLC

Inventor： Quoc V. Le ,  Minh-Thang Luong ,  Ilya Sutskever ,  Oriol Vinyals ,  Wojciech Zaremba

IPC: G06F17/28 ,  G06F17/27 ,  G06F7/02 ,  G06F7/10 ,  G10L15/02 ,  G10L15/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural translation systems with rare word processing. One of the methods is a method training a neural network translation system to track the source in source sentences of unknown words in target sentences, in a source language and a target language, respectively and includes deriving alignment data from a parallel corpus, the alignment data identifying, in each pair of source and target language sentences in the parallel corpus, aligned source and target words; annotating the sentences in the parallel corpus according to the alignment data and a rare word model to generate a training dataset of paired source and target language sentences; and training a neural network translation model on the training dataset.