• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Jiang, ZongLi (Jiang, ZongLi.) (学者:蒋宗礼) | Zhang, Shuo (Zhang, Shuo.)

收录:

EI

摘要:

The traditional end-to-end task-oriented dialogue models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. But in the case of large amounts of data, there are many types of questions. It performs poorly when answering multiple types of questions, memory information cannot effectively record all the sentence information of the context. In view of the above this, this article uses a modified transformer model to overcome the problems mentioned in dialogue tasks. Transformer is a model constructed using attention mechanisms, which completely discards the method of RNN (recurrent neural networks), and its structure includes two sub-parts of Encoder and decoder. It uses residual network, batch normalization, and self-attention mechanism to build the model structure, uses Positional Encoding to capture sentence information, which can speed up model training convergence and capture Longer sentence information. In this paper, we modified the activation function in the transformer and use label smoothing to optimize the training to make the model's expressive ability better than previous. © 2019 Published under licence by IOP Publishing Ltd.

关键词:

Convolutional neural networks Decoding Intelligent computing Recurrent neural networks Signal encoding

作者机构:

  • [ 1 ] [Jiang, ZongLi]Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 2 ] [Zhang, Shuo]Faculty of Information Technology, Beijing University of Technology, Beijing, China

通讯作者信息:

  • 蒋宗礼

    [jiang, zongli]faculty of information technology, beijing university of technology, beijing, china

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

ISSN: 1742-6588

年份: 2020

期: 1

卷: 1544

语种: 英文

被引次数:

WoS核心集被引频次: 0

SCOPUS被引频次:

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 2

归属院系:

在线人数/总访问数:646/3573191
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司