公开(公告)号：US20210397780A1

公开(公告)日：2021-12-23

申请号：US17405813

申请日：2021-08-18

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

Inventor： Chao PANG ,  Shuohuan WANG ,  Yu SUN ,  Zhi LI

IPC: G06F40/166 ,  G06K9/46 ,  G06K9/62 ,  G06N20/00

Abstract: A method for correcting an error in a text, an electronic device, and a storage medium are provided. The method includes: obtaining an original text; obtaining a training text by preprocessing the original text; extracting a plurality of feature vectors corresponding to each word in the training text; obtaining an input vector by processing the plurality of feature vectors; obtaining a target text by inputting the input vector into a text error correction model; and adjusting parameters of the text error correction model based on a difference between the target text and the original text.

公开(公告)号：US20220171941A1

公开(公告)日：2022-06-02

申请号：US17348104

申请日：2021-06-15

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

Inventor： Xuan OUYANG ,  Shuohuan WANG ,  Chao PANG ,  Yu SUN ,  Hao TIAN ,  Hua WU ,  Haifeng WANG

IPC: G06F40/30 ,  G06F40/58 ,  G06N20/00

Abstract: The present disclosure provides a multi-lingual model training method, apparatus, electronic device and readable storage medium and relates to the technical field of deep learning and natural language processing. A technical solution of the present disclosure when training the multi-lingual model is: obtaining training corpuses comprising a plurality of bilingual corpuses and a plurality of monolingual corpuses; training a multi-lingual model with a first training task by using the plurality of bilingual corpuses; training the multi-lingual model with a second training task by using the plurality of monolingual corpuses; and completing the training of the multi-lingual model in a case of determining that loss functions of the first training task and second training task converge. In the present disclosure, the multi-lingual model can be enabled to achieve semantic interaction between different languages and improve the accuracy of the multi-lingual model in learning the semantic representations of the multi-lingual model.

公开(公告)号：US20210192141A1

公开(公告)日：2021-06-24

申请号：US16939947

申请日：2020-07-27

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

Inventor： Chao PANG ,  Shuohuan WANG ,  Yu SUN ,  Zhi LI

IPC: G06F40/30 ,  G06N20/00

Abstract: A method for generating a vector representation of a text includes dividing the text into text segments. Each text segment is represented as a segment vector corresponding to the respective text segment by employing a first-level semantic model. The segment vector is configured to indicate a semantics of the text segment. Text semantics recognition is performed on the segment vector of each text segment by employing a second-level semantic model to obtain a text vector for indicating a topic of the text.

公开(公告)号：US20210248498A1

公开(公告)日：2021-08-12

申请号：US17241999

申请日：2021-04-27

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

Inventor： Chao PANG ,  Shuohuan WANG ,  Yu SUN ,  Zhi LI

IPC: G06N5/04 ,  G06F40/30 ,  G06N20/00

Abstract: A method for training a pre-trained knowledge model includes: obtaining a training text, in which the training text includes a structured knowledge text and an article corresponding to the structured knowledge text, and the structured knowledge text includes a head node, a tail node, and a relationship between the head node and the tail node; and training a pre-trained knowledge model to be trained according to the training text.

公开(公告)号：US20220198327A1

公开(公告)日：2022-06-23

申请号：US17348270

申请日：2021-06-15

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

Inventor： Shuohuan WANG ,  Chao PANG ,  Yu SUN

IPC: G06N20/00 ,  G06N5/02 ,  G10L25/54 ,  G10L25/27 ,  G06F16/9032 ,  G06F16/907

Abstract: The present disclosure provides a method, apparatus, device and storage medium for training a dialogue understanding model, and relates to technical field of computers, and specifically to the technical field of artificial intelligence such as natural language processing and deep learning. The method for training a dialogue understanding model includes: obtaining dialogue understanding training data; performing joint training for a dialogue understanding pre-training task and a general pre-training task by using the dialogue understanding training data, to obtain a dialogue understanding model. According to the present disclosure, a model specially adapted for a dialogue understanding task may be obtained by training.

公开(公告)号：US20210374344A1

公开(公告)日：2021-12-02

申请号：US17094943

申请日：2020-11-11

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

Inventor： Shuohuan WANG ,  Chao PANG ,  Yu SUN

IPC: G06F40/284 ,  G06N20/00 ,  G06F16/23 ,  G06F7/08

Abstract: A method for resource sorting, a method for training a sorting model and corresponding apparatuses which relate to the technical field of natural language processing under artificial intelligence are disclosed. The method according to some embodiments includes: forming an input sequence in order with an item to be matched and information of candidate resources; performing Embedding processing on each Token in the input sequence, the Embedding processing including: word Embedding, position Embedding and statement Embedding; and inputting result of the Embedding processing in a sorting model to obtain sorting scores of the sorting model for the candidate resources, the sorting model is obtained by pre-training of a Transformer model.