公开(公告)号：US20210248484A1

公开(公告)日：2021-08-12

申请号：US17205894

申请日：2021-03-18

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

Inventor： Shuohuan WANG ,  Siyu DING ,  Yu SUN

IPC: G06N5/02 ,  G06K9/62 ,  G06F40/279

Abstract: The disclosure discloses a method and an apparatus for generating a semantic representation model, and a storage medium. The detailed implementation includes: performing recognition and segmentation on the original text included in an original text set to obtain knowledge units and non-knowledge units in the original text; performing knowledge unit-level disorder processing on the knowledge units and the non-knowledge units in the original text to obtain a disorder text; generating a training text set based on the character attribute of each character in the disorder text; and training an initial semantic representation model by employing the training text set to generate the semantic representation model.

公开(公告)号：US20210383064A1

公开(公告)日：2021-12-09

申请号：US17101789

申请日：2020-11-23

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

Inventor： Shuohuan WANG ,  Siyu DING ,  Yu SUN ,  Hua WU ,  Haifeng WANG

IPC: G06F40/279 ,  G06F40/166 ,  G06F40/30 ,  G06N20/00

Abstract: The disclosure provides a text recognition method, an electronic device, and a storage medium. The method includes: obtaining N segments of a sample text; inputting each of the N segments into a preset initial language model in sequence, to obtain first text vector information corresponding to the N segments; inputting each of the N segments into the initial language model in sequence again, to obtain second text vector information corresponding to a currently input segment; in response to determining that the currently input segment has the mask, predicting the mask according to the second text vector information and the first text vector information to obtain a predicted word at a target position corresponding to the mask; training the initial language model according to an original word and the predicted word to generate a long text language model; and recognizing an input text through the long text language model.

公开(公告)号：US20210334659A1

公开(公告)日：2021-10-28

申请号：US17369699

申请日：2021-07-07

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

Inventor： Siyu DING ,  Shuohuan WANG ,  Yu SUN

IPC: G06N3/08 ,  G06N3/04

Abstract: The present application discloses a method and an apparatus for adversarial training of a machine learning (ML) model and a medium. The method includes: obtaining input information in a training sample; extracting features of a plurality of input characters in the input information; inputting the features of the plurality of input characters to the ML model, to capture an attention weight on an input character of the plurality of input characters by an attention layer of the ML model; disturbing the attention weight captured by the attention layer, so that the ML model outputs a predicted character according to the attention weight disturbed; and training the ML model according to a difference between the predicted character and a labeled character in the training sample.