公开(公告)号：US20180365208A1

公开(公告)日：2018-12-20

申请号：US15934496

申请日：2018-03-23

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

Inventor： Liqun ZHENG ,  Jinbo ZHAN ,  Qiugen XIAO ,  Zhihong FU ,  Jingzhou HE ,  Guyue ZHOU

IPC: G06F17/27 ,  G06N3/08

Abstract: Embodiments of the present disclosure disclose a method for modifying a segmentation model based on artificial intelligence, a device and a storage medium. The method may include: acquiring a model parameter of the segmentation model, and performing a training on a feature vector corresponding to a preset generalized feature of a first training corpus via a neural network so as to acquire a model parameter of the preset generalized feature; performing a word segmentation on the first training corpus according to the model parameter of the segmentation model and the model parameter of the preset generalized feature, so as to acquire a segmentation result; and comparing the segmentation result with the first training corpus according to a preset rule, and modifying the model parameter of the segmentation model and a parameter of the neural network according to a comparison result.

公开(公告)号：US20190095447A1

公开(公告)日：2019-03-28

申请号：US16054966

申请日：2018-08-03

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

Inventor： Qiugen XIAO ,  Jinbo ZHAN ,  Kunsheng ZHOU ,  Liqun ZHENG ,  Zhihong FU ,  Jingzhou HE

IPC: G06F17/30 ,  G06N99/00

Abstract: Embodiments of the disclosure disclose a method, apparatus, device, and storage medium for establishing an error correction model based on an error correction platform. The method comprises: determining a target error correction level based on an error correction need of a user; and selecting at least one error correction module from each of at least two error correcting portions of the error correction platform based on the target error correction level, and combining the selected error correction module to form an error correction model.

公开(公告)号：US20180365217A1

公开(公告)日：2018-12-20

申请号：US15934410

申请日：2018-03-23

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

Inventor： Liqun ZHENG ,  Jinbo ZHAN ,  Qiugen XIAO ,  Zhihong FU ,  Jingzhou HE ,  Guyue ZHOU

IPC: G06F17/27 ,  G06F17/28

Abstract: Embodiments of the present disclosure disclose a word segmentation method based on artificial intelligence, a server and a storage medium. The word segmentation method may include: acquiring a corpus to be segmented and a segmentation model corresponding to a preset segmentation template; matching the corpus to be segmented with the segmentation model according to a preset matching algorithm, and acquiring a target phrase satisfying a first preset rule in the corpus to be segmented; modifying an emission matrix corresponding to the segmentation model and the corpus to be segmented according to the target phrase; and performing a word segmentation on the corpus to be segmented according to the emission matrix modified, to acquire a first segmentation result.