公开(公告)号：US10650102B2

公开(公告)日：2020-05-12

申请号：US15900166

申请日：2018-02-20

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Pengkai Li ,  Jingzhou He ,  Zhihong Fu ,  Xianwei Xin

IPC: G06F17/27 ,  G06F17/28 ,  G06N3/08 ,  G06F16/951 ,  G06N3/04 ,  G06F16/33

Abstract: The present disclosure discloses a method and apparatus for generating a parallel text in the same language. The method comprises: acquiring a source segmented word sequence and a pre-trained word vector table; determining a source word vector sequence corresponding to the source segmented word sequence, according to the word vector table; importing the source word vector sequence into a first pre-trained recurrent neural network model, to generate an intermediate vector of a preset dimension for characterizing semantics of the source segmented word sequence; importing the intermediate vector into a second pre-trained recurrent neural network model, to generate a target word vector sequence corresponding to the intermediate vector; and determining a target segmented word sequence corresponding to the target word vector sequence according to the word vector table, and determining the target segmented word sequence as a parallel text in the same language corresponding to the source segmented word sequence.

公开(公告)号：US20180365231A1

公开(公告)日：2018-12-20

申请号：US15900166

申请日：2018-02-20

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Pengkai Li ,  Jingzhou He ,  Zhihong Fu ,  Xianwei Xin

IPC: G06F17/28 ,  G06F17/30 ,  G06N3/08

Abstract: The present disclosure discloses a method and apparatus for generating a parallel text in the same language. The method comprises: acquiring a source segmented word sequence and a pre-trained word vector table; determining a source word vector sequence corresponding to the source segmented word sequence, according to the word vector table; importing the source word vector sequence into a first pre-trained recurrent neural network model, to generate an intermediate vector of a preset dimension for characterizing semantics of the source segmented word sequence;importing the intermediate vector into a second pre-trained recurrent neural network model, to generate a target word vector sequence corresponding to the intermediate vector; and determining a target segmented word sequence corresponding to the target word vector sequence according to the word vector table, and determining the target segmented word sequence as a parallel text in the same language corresponding to the source segmented word sequence.