公开(公告)号：US20230086145A1

公开(公告)日：2023-03-23

申请号：US17936761

申请日：2022-09-29

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

Inventor： Wenbin JIANG ,  Yajuan LV ,  Yong ZHU ,  Hua WU ,  Haifeng WANG

IPC: G06F16/738 ,  G06N5/02

Abstract: A method of processing data, a device, and a medium are provided, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision, natural language technology, speech technology, deep learning and knowledge graph. The method of processing data includes: generating a video feature, a question feature and an answer feature based on acquired video data, acquired question data and acquired candidate answer data; determining a link relationship between the video feature, the question feature and the answer feature; and determining a matching result for the video data, the question data and the candidate answer data based on the link relationship.

公开(公告)号：US20230018489A1

公开(公告)日：2023-01-19

申请号：US17862519

申请日：2022-07-12

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

Inventor： Wenbin JIANG ,  Yajuan LYU ,  Yong ZHU ,  Hua WU ,  Haifeng WANG

IPC: G06F16/242 ,  G06F16/21 ,  G06F16/245 ,  G06N5/02

Abstract: The present disclosure discloses a method for acquiring a structured question-answering (QA) model, a QA method and corresponding apparatuses, and relates to knowledge graph and deep learning technologies in the field of artificial intelligence technologies. A specific implementation solution involves: acquiring training samples corresponding to N structured QA database types, the training samples including question samples, information of the structured QA database types and query instruction samples used by the question samples to query structured QA databases of the types, N being an integer greater than 1; and training a text generation model by using the training samples to obtain the structured QA model, wherein the question samples and the information of the structured QA database types are taken as input to the text generation model, and the query instruction samples are taken as target output of the text generation model.

公开(公告)号：US20220293092A1

公开(公告)日：2022-09-15

申请号：US17828773

申请日：2022-05-31

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

Inventor： Siyu DING ,  Chao PANG ,  Shuohuan WANG ,  Yanbin ZHAO ,  Junyuan SHANG ,  Yu SUN ,  Shikun FENG ,  Hao TIAN ,  Hua WU ,  Haifeng WANG

IPC: G10L15/06 ,  G10L15/02 ,  G10L15/18

Abstract: The present application provides a method of training a natural language processing model, which relates to a field of artificial intelligence, and in particular to a field of natural language processing. A specific implementation scheme includes: performing a semantic learning for multi-tasks on an input text, so as to obtain a semantic feature for the multi-tasks, wherein the multi-tasks include a plurality of branch tasks; performing a feature learning for each branch task based on the semantic feature, so as to obtain a first output result for each branch task; calculating a loss for each branch task according to the first output result for the branch task; and adjusting a parameter of the natural language processing model according to the loss for each branch task. The present application further provides a method of processing a natural language, an electronic device, and a storage medium.

公开(公告)号：US20220292269A1

公开(公告)日：2022-09-15

申请号：US17502108

申请日：2021-10-15

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

Inventor： Guocheng NIU ,  Wei LI ,  Can GAO ,  Xinyan XIAO ,  Hua WU

IPC: G06F40/58 ,  G06F40/47 ,  G06F40/205

Abstract: The present disclosure discloses a method and apparatus for acquiring a pre-trained model, and relates to natural language processing and deep learning technologies in the field of artificial intelligence technologies. An implementation includes: acquiring training data, the training data including a single-modal language material and a multi-modal language material, and the multi-modal language material including a language material pair formed by a first-modal language material and a second-modal language material; and performing a multi-task training operation on a pre-trained model using the training data, the multi-task including at least one cross-modal contrastive learning task and at least one single-modal learning task; the pre-trained language model obtained in the present disclosure may learn from different forms of language materials, i.e., the single-modal language material and the multi-modal language material, such that the pre-trained language model may effectively process information in various modals.

公开(公告)号：US20210192364A1

公开(公告)日：2021-06-24

申请号：US17124030

申请日：2020-12-16

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

Inventor： Haifeng WANG ,  Wenbin JIANG ,  Yajuan LV ,  Yong ZHU ,  Hua WU

IPC: G06N5/02 ,  G06F40/30 ,  G06F40/279 ,  G06K9/62

Abstract: The present application discloses a text processing method and device based on natural language processing and a knowledge graph, and relates to the in-depth field of artificial intelligence technology. A specific implementation is: an electronic device uses a joint learning model to obtain a semantic representation, which is obtained by the joint learning model by combining knowledge graph representation learning and natural language representation learning, it combines a knowledge graph representation learning and a natural language representation learning, compared to using only the knowledge graph representation learning or the natural language representation learning to learn semantic representation of a prediction object, factors considered by the joint learning model are more in quantity and comprehensiveness, so accuracy of semantic representation can be improved, and thus accuracy of text processing can be improved.