公开(公告)号：US11928432B2

公开(公告)日：2024-03-12

申请号：US17319189

申请日：2021-05-13

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

Inventor： Fei Yu ,  Jiji Tang ,  Weichong Yin ,  Yu Sun ,  Hao Tian ,  Hua Wu ,  Haifeng Wang

IPC: G06F40/30 ,  G06F40/284 ,  G06N5/04 ,  G06N20/00 ,  G06V10/80 ,  G06V20/30

CPC classification number: G06F40/284 ,  G06F40/30 ,  G06N5/04 ,  G06N20/00 ,  G06V10/811 ,  G06V20/30

Abstract: A multi-modal pre-training model acquisition method, an electronic device and a storage medium, which relate to the fields of deep learning and natural language processing, are disclosed. The method may include: determining, for each image-text pair as training data, to-be-processed fine-grained semantic word in the text; masking the to-be-processed fine-grained semantic words; and training the multi-modal pre-training model using the training data with the fine-grained semantic words masked.

公开(公告)号：US11461549B2

公开(公告)日：2022-10-04

申请号：US16988907

申请日：2020-08-10

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

Inventor： Han Zhang ,  Dongling Xiao ,  Yukun Li ,  Yu Sun ,  Hao Tian ,  Hua Wu ,  Haifeng Wang

IPC: G06F40/274 ,  G06F40/56 ,  G06F40/30 ,  G06K9/62

Abstract: The present disclosure discloses a method and an apparatus for generating a text based on a semantic representation and relates to a field of natural language processing (NLP) technologies. The method for generating the text includes: obtaining an input text, the input text comprising a source text; obtaining a placeholder of an ith word to be predicted in a target text; obtaining a vector representation of the ith word to be predicted, in which the vector representation of the ith word to be predicted is obtained by calculating the placeholder of the ith word to be predicted, the source text and 1st to (i−1)th predicted words by employing a self-attention mechanism; and generating an ith predicted word based on the vector representation of the ith word to be predicted, to obtain a target text.