公开(公告)号：US20230051373A1

公开(公告)日：2023-02-16

申请号：US17974317

申请日：2022-10-26

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

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

IPC: G06F40/47

Abstract: A method for training a non-autoregressive translation (NAT) model includes: acquiring a source language text, a target language text corresponding to the source language text and a target length of the target language text; generating a target language prediction text and a prediction length by inputting the source language text into the NAT model, in which initialization parameters of the NAT model are determined based on parameters of a pre-trained translation model; and obtaining a target NAT model by training the NAT model based on the target language text, the target language prediction text, the target length and the prediction length.

公开(公告)号：US20220391602A1

公开(公告)日：2022-12-08

申请号：US17820765

申请日：2022-08-18

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

Inventor： Haifeng WANG ,  Zhanyi LIU ,  Zhongjun HE ,  Hua WU ,  Zhi LI ,  Xing WAN ,  Jingxuan ZHAO ,  Ruiqing ZHANG ,  Chuanqiang ZHANG ,  Fengtao HUANG ,  Hanbing SONG ,  Wei DI ,  Shuangshuang CUI ,  Yongzheng XIN

IPC: G06F40/58 ,  G06V30/19

Abstract: A display method, an electronic device, and a storage medium, which relate to a field of natural language processing and a field of display. The display method includes: acquiring a content to be displayed; extracting a target term from the content using a term extraction rule; acquiring an annotation information for at least one target term, responsive to an extraction of the at least one target term; and displaying the annotation information for the at least one target term and the content.