公开(公告)号：US20230095352A1

公开(公告)日：2023-03-30

申请号：US18074853

申请日：2022-02-05

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Ruiqing ZHANG ,  Hui LIU ,  Zhongjun HE ,  Zhi LI ,  Hua WU

IPC: G06N3/0455 ,  G06F40/44 ,  G06F40/58 ,  G06N3/08 ,  G06N3/042

Abstract: The present disclosure provides a translation method and apparatus, an electronic device, and a non-transitory storage medium. An implementation includes: determining an encoded feature of a sentence to be translated by an encoding module; determining, by a graph network module, a knowledge fusion feature of the sentence to be translated based on a preset graph network, wherein the preset graph network is constructed based on a polysemous word in a source language corresponding to the sentence to be translated and a plurality of translated words corresponding to the polysemous word in a target language; determining, by a decoding network, a translated sentence corresponding to the sentence to be translated based on the encoded feature and the knowledge fusion feature.

公开(公告)号：US20230342561A1

公开(公告)日：2023-10-26

申请号：US18122316

申请日：2023-03-16

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

Inventor： Ruiqing ZHANG ,  Hui LIU ,  Zhongjun HE ,  Zhi LI ,  Hua WU

IPC: G06F40/47 ,  G06F40/51

CPC classification number: G06F40/47 ,  G06F40/51

Abstract: A machine translation method includes: obtaining first target language text by performing first translation on source language text using an initial NMT model; identifying an untranslated part in the source language text based on the source language text and the first target language text; obtaining an adjusted NMT model by increasing an attention weight corresponding to the untranslated part in the initial NMT mode; and obtaining second target language text by performing second translation on the source language text using the adjusted NMT model.

公开(公告)号：US20230153543A1

公开(公告)日：2023-05-18

申请号：US17951216

申请日：2022-09-23

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

Inventor： Ruiqing ZHANG ,  Xiyang WANG ,  Hui LIU ,  Zhongjun HE ,  Zhi LI ,  Hua WU

IPC: G06F40/51 ,  G06F40/42

CPC classification number: G06F40/51 ,  G06F40/42

Abstract: A translation method, a model training method, apparatuses, electronic devices and storage mediums, which relate to the field of artificial intelligence technologies, such as machine learning technologies, information processing technologies, are disclosed. In an implementation, a weight for each translation model in at least two pre-trained translation models translating a to-be-translated specified sentence is acquired based on the specified sentence and a pre-trained weighting model; and the specified sentence is translating using the at least two translation models based on the weight for each translation model translating the specified sentence.