公开(公告)号：US20220092252A1

公开(公告)日：2022-03-24

申请号：US17212331

申请日：2021-03-25

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

Inventor： Wenhao Wu ,  Wei Li ,  Xinyan Xiao

IPC: G06F40/126 ,  G06F40/284 ,  G06N5/02 ,  G06K9/62

Abstract: A method for generating a summary, an electronic device and a storage medium thereof, which relate to the natural language processing field, the deep learning field and the knowledge graph field, are disclosed. The method may include: acquiring a knowledge graph corresponding to a text to be processed, in the graph, nodes represent semantic concepts, and sides represent semantic relationships among the semantic concepts; encoding the text at a token level to obtain a context encoded representation of each token; determining an initial representation of each node in the knowledge graph according to the context encoded representation of each token; performing an encoding operation according to the initial representation of each node and the connection relationships among the nodes to obtain a node representation of each node; and performing a decoding operation according to the node representation of each node to obtain the summary of the text to be processed.

公开(公告)号：US11574133B2

公开(公告)日：2023-02-07

申请号：US17133381

申请日：2020-12-23

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

Inventor： Wei Li ,  Xinyan Xiao ,  Hua Wu ,  Haifeng Wang

IPC: G06F40/56 ,  G06F40/58

Abstract: The disclosure may provide a method for obtaining a document layout, an electronic device, and a storage medium. The method may include: obtaining a plurality of pieces of first sample data; extracting structured information from each of the plurality of pieces of first sample data as target structured information corresponding to each of the plurality of pieces of first sample data; inputting the plurality of pieces of first sample data into an initial text generation model to generate predicted structured information corresponding to each of the plurality of pieces of first sample data; generating a first loss value based on a difference between the predicted structured information corresponding to each of the plurality of pieces of first sample data and the corresponding target structured information; and training a phrase generation ability of the initial text generation model based on the first loss value to generate the text generation model.