公开(公告)号：US20220180058A1

公开(公告)日：2022-06-09

申请号：US17383611

申请日：2021-07-23

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

Inventor： Ruiqing ZHANG ,  Chuanqiang ZHANG ,  Zhongjun HE ,  Zhi LI ,  Hua WU

IPC: G06F40/232 ,  G06F40/40 ,  G06F40/253

Abstract: The present disclosure provides a text error correction method, apparatus, electronic device and storage medium, and relates to the technical field of artificial intelligence such as natural language processing and deep learning. A specific implementation solution is: obtaining a current sentence and a historical sentence of the current sentence in an article to which the current sentence belongs; performing text error correction processing on the current sentence based on the current sentence and the historical sentence. According to the technical solutions of the present disclosure, text error correction can be performed on the current sentence based on the historical sentence, namely, the upper contextual information, of the current sentence in the article, so that the error correction information is richer and the error correction result is more accurate.

公开(公告)号：US20210248309A1

公开(公告)日：2021-08-12

申请号：US17243097

申请日：2021-04-28

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

Inventor： Ruiqing ZHANG ,  Chuanqiang ZHANG ,  Zhongjun HE ,  Zhi LI ,  Hua WU

IPC: G06F40/166 ,  G06F40/279 ,  G06N20/00

Abstract: A method for text error correction includes: obtaining a text to be corrected; obtaining a pinyin sequence of the text to be corrected; and inputting the text to be corrected and the pinyin sequence to a text error correction model, to obtain a corrected text.

公开(公告)号：US20210192147A1

公开(公告)日：2021-06-24

申请号：US16868426

申请日：2020-05-06

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

Inventor： Ruiqing ZHANG ,  Chuanqiang ZHANG ,  Hao XIONG ,  Zhongjun HE ,  Hua WU ,  Zhi LI ,  Haifeng WANG

IPC: G06F40/40

Abstract: Embodiments of the present disclosure provide a method and an apparatus for translating a polysemy, and a medium. The method includes: obtaining a source language text; identifying and obtaining the polysemy from the source language text; inquiring related words corresponding to each interpretation of the polysemy; determining a target interpretation corresponding to the related words contained in the source language text; and translating the polysemy into the target interpretation.

公开(公告)号：US20240220812A1

公开(公告)日：2024-07-04

申请号：US17474950

申请日：2021-09-14

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

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

IPC: G06N3/094

CPC classification number: G06N3/094

Abstract: A method for training a machine translation (MT) model and an electronic device are provided. The technical solution includes: obtaining an original training sample configured to train an MT model; generating at least one adversarial training sample of the MT model based on the original training sample; training the MT model based on the original training sample and the adversarial training sample.

公开(公告)号：US20230342560A1

公开(公告)日：2023-10-26

申请号：US18121351

申请日：2023-03-14

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

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

IPC: G06F40/47 ,  G06F40/166 ,  G06F40/30

CPC classification number: G06F40/47 ,  G06F40/166 ,  G06F40/30 ,  G06F40/247

Abstract: A text translation method is described that includes initially acquiring text. Thereafter, first text is determined in the initial text; and second text is determined according to the first text, where the second text is used for describing the first text. Additionally, initial text is translated to obtain initial translation text, and the second text is translated to obtain description translation text. Thereafter, the initial translation text is updated according to the description translation text to obtain target translation text of the initial text.

公开(公告)号：US20210326538A1

公开(公告)日：2021-10-21

申请号：US17362628

申请日：2021-06-29

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

Inventor： Chuanqiang ZHANG ,  Ruiqing ZHANG ,  Zhi LI ,  Zhongjun HE ,  Hua WU

IPC: G06F40/58 ,  G06F40/30

Abstract: A method for text translation includes obtaining a text to be translated; and inputting the text to be translated into a text translation model. The trained text translation model divides the text to be translated into a plurality of semantic units, determines N semantic units before a current semantic unit among the plurality of semantic units as local context semantic units, determines M semantic units before the local context semantic units as global context semantic units, and generates a translation result of the current semantic unit based on the local context semantic units and the global context semantic units. N is an integer, and M is an integer.

公开(公告)号：US20210192150A1

公开(公告)日：2021-06-24

申请号：US16926197

申请日：2020-07-10

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

Inventor： Ruiqing ZHANG ,  Chuanqiang ZHANG ,  Hao XIONG ,  Zhongjun HE ,  Hua WU ,  Haifeng WANG

IPC: G06F40/55 ,  G06F40/58 ,  G06F40/211

Abstract: Embodiments of the present disclosure provide a language conversion method and apparatus based on syntactic linearity and a non-transitory computer-readable storage medium. The method includes: encoding a source sentence to be converted by using a preset encoder to determine a first vector and a second vector corresponding to the source sentence; determining a current mask vector according to a preset rule, in which the mask vector is configured to modify vectors output by the preset encoder; determining a third vector according to target language characters corresponding to source characters located before a first source character; and decoding the first vector, the second vector, the mask vector, and the third vector by using a preset decoder to generate a target character corresponding to the first source character.