Title:
語義表現モデルの訓練方法、装置、デバイス及び記憶媒体
Document Type and Number:
Japanese Patent JP7358698
Kind Code:
B2
Abstract:
Disclosed are a method for training a semantic representation model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the field of artificial intelligence, such as a natural language processing technology, a deep learning technology, or the like. The method for training a semantic representation model includes: obtaining an anchor sample based on a sentence, and obtaining a positive sample and a negative sample based on syntactic information of the sentence; processing the anchor sample, the positive sample and the negative sample using the semantic representation model respectively, so as to obtain an anchor-sample semantic representation, a positive-sample semantic representation and a negative-sample semantic representation; constructing a contrast loss function based on the anchor-sample semantic representation, the positive-sample semantic representation, and the negative-sample semantic representation; and training the semantic representation model based on the contrast loss function.
Inventors:
Jan, Shuai
One, Lizier
Xiao and Shin Yang
Chan, Yue
One, Lizier
Xiao and Shin Yang
Chan, Yue
Application Number:
JP2022031735A
Publication Date:
October 11, 2023
Filing Date:
March 02, 2022
Export Citation:
Assignee:
Beijing Baidu Netcom Science Technology Co., Ltd.
International Classes:
G06F16/36
Domestic Patent References:
| JP2020181486A | ||||
| JP2019509551A | ||||
| JP2017049681A | ||||
| JP2006031198A |
Foreign References:
| CN111143530A | ||||
| CN109918663A | ||||
| US20200380298 | ||||
| CN112733550A | ||||
| US20210182662 | ||||
| US20200097742 |
Attorney, Agent or Firm:
Patent Attorney Corporation RYUKA International Patent Office
Previous Patent: marking aid
Next Patent: Proton conductive electrolyte for reversible solid oxide batteries
Next Patent: Proton conductive electrolyte for reversible solid oxide batteries