公开(公告)号：US20250094877A1

公开(公告)日：2025-03-20

申请号：US18969719

申请日：2024-12-05

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

Inventor： Fan WANG ,  Hua WU ,  Yingzhan LIN ,  Zengfeng ZENG ,  Yufeng HU ,  Jianhui DING ,  Haifeng WANG

IPC: G06N20/00

Abstract: A large model-based method of generating a text, a method of training a text generation model, a device, and a medium are provided, which relate to a field of artificial intelligence technology, specifically to fields of deep learning, natural language processing and large model technologies. The large model-based method of generating a text includes: acquiring a memory state for a text to be processed, where the memory state is generated based on a previous text of the text to be processed; determining an embedding feature of the text to be processed as an initial hidden state, and processing the memory state and the initial hidden state by using a first attention mechanism to obtain an updated hidden state; and generating a subsequent text for the text to be processed based on the updated hidden state.

公开(公告)号：US20230214688A1

公开(公告)日：2023-07-06

申请号：US18119494

申请日：2023-03-09

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

Inventor： Jiyuan ZHANG ,  Jianguo MAO ,  Zengfeng ZENG ,  Weihua PENG ,  Wenbin JIANG ,  Yajuan LYU

IPC: G06N5/04

CPC classification number: G06N5/04

Abstract: A method and apparatus for determining an answer to a question are provided. The method includes: splicing an acquired to-be-queried question with each candidate answer into each question-answer pair; performing reasoning operations of feature combination parameters on different granularity features of each question-answer pair at a preset number of steps in a horizontal direction based on recurrent characteristics of a recurrent neural network; determining feature combination weights of the different granularity features using multiple preset vertical reasoning layers at different reasoning focuses respectively, at each step of the reasoning operations in the horizontal direction; obtaining a candidate answer feature corresponding to each question-answer pair, respectively, through a final step of the reasoning operations; and determining a target candidate answer matching the to-be-queried question based on a feature similarity between a question feature of the to-be-queried question and each candidate answer feature.