公开(公告)号：US20210397794A1

公开(公告)日：2021-12-23

申请号：US17249718

申请日：2021-03-10

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

Inventor： Xuyi CHEN ,  Shiwei HUANG

IPC: G06F40/30 ,  G06N3/04 ,  G06N3/08

Abstract: Embodiments of a method and an apparatus for improving a model based on a pre-trained semantic model are provided. The method may include: based on the pre-trained semantic model, obtaining an initial improved model, where semantic result information of an input vector is determined in the initial improved model based on a hash search method; and based on a model distillation method, training the initial improved model to obtain an improved model. Some embodiments can obtain the semantic result information of the input vector by performing the hash search method on the input vector, replace the original complex iterative calculation process of a semantic model, and obtain the improved model with few model parameters and high compression ratio.

公开(公告)号：US20210201198A1

公开(公告)日：2021-07-01

申请号：US16945183

申请日：2020-07-31

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

Inventor： Weibin LI ,  Zhifan ZHU ,  Weiyue SU ,  Jingzhou HE ,  Shikun FENG ,  Yuhui CAO ,  Xuyi CHEN ,  Danxiang ZHU

IPC: G06N20/00 ,  G06F16/901

Abstract: A method for generating node representations in a heterogeneous graph, an electronic device, and a non-transitory computer-readable storage medium, and relates to the field of machine learning technologies. The method includes: acquiring a heterogeneous graph; inputting the heterogeneous graph into a heterogeneous graph learning model to generate a node representation of each node in the heterogeneous graph, in which the heterogeneous graph learning model generates the node representation of each node by actions of: segmenting the heterogeneous graph into a plurality of subgraphs, in which each subgraph includes nodes of two types and an edge of one type between the nodes of two types; and generating the node representation of each node according to the plurality of subgraphs.

公开(公告)号：US20210192288A1

公开(公告)日：2021-06-24

申请号：US16895242

申请日：2020-06-08

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

Inventor： Yuhui CAO ,  Shikun FENG ,  Xuyi CHEN ,  Jingzhou HE

IPC: G06K9/62 ,  G10L25/27 ,  G06N20/00

Abstract: Embodiments of the present disclosure provide a method and apparatus for processing data. The method may include: acquiring a sample set; inputting a plurality of target samples in the sample set into a pre-trained first natural language processing model, respectively, to obtain prediction results output from the pre-trained first natural language processing model; determining the obtained prediction results as labels of the target samples in the plurality of target samples, respectively; and training a to-be-trained second natural language processing model, based on the plurality of target samples and the labels of the target samples to obtain a trained second natural language processing model, parameters in the first natural language processing model being more than parameters in the second natural language processing model.