• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

张丽 (张丽.) | 王月怡 (王月怡.)

Indexed by:

incoPat zhihuiya

Abstract:

本发明公开了一种基于深度学习的文本分类方法,首先进行噪音清除,包含去除标点符号、特殊字符。构建字典、依据字典构建数据集;词嵌入和对抗训练;训练双向长短时记忆网络层;训练注意力机制层;计算输出结果。本发明方法将广泛应用于图像领域的对抗训练方法应用于自然语言处理领域,通过在深度神经网络中添加对抗扰动,使得模型训练过程中网络向loss增大的方向改变,利用loss对输入求导从而更新参数,从而降低模型对于对抗扰动的敏感性,有效地缓解模型过拟合,提高文本分类效果。

Keyword:

Reprint Author's Address:

Email:

Show more details

Related Keywords:

Related Article:

Patent Info :

Type: 发明申请

Patent No.: CN202111662807.8

Filing Date: 2021-12-31

Publication Date: 2024-05-28

Pub. No.: CN114357166B

Applicants: 北京工业大学

Legal Status: 授权

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 14

Affiliated Colleges:

Online/Total:649/10654573
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.