• 中文
    • English
  • English 
    • 中文
    • English
  • Login
View Item 
  •   DSpace Home
  • 软件学院(撤)
  • 软件学院-已发表论文
  • View Item
  •   DSpace Home
  • 软件学院(撤)
  • 软件学院-已发表论文
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

一种基于循环神经网络的古文断句方法
A Sentence Segmentation Method for Ancient Chinese Texts Based on Recurrent Neural Network

Thumbnail
Full Text
一种基于循环神经网络的古文断句方法.pdf (1.063Mb)
Date
2017
Author
王博立
史晓东
苏劲松
Collections
  • 软件学院-已发表论文 [471]
Show full item record
Abstract
提出一种基于循环神经网络的古文自动断句方法。该方法采用基于GRU (gated recurrent; unit)的双向循环神经网络进行古文断句。在解码过程中, 该算法不仅利用神经网络输出的概率分布, 还进一步引入状态转移概率和长度惩罚,; 以便提高断句准确率。在大规模古籍语料上的实验结果表明, 所提方法能够取得比传统方法更高的断句F1值。
 
This paper proposes an automatic sentence segmentation method for; ancient Chinese texts based on recurrent neural network (RNN). A; bi-directional RNN structure with gated recurrent units (GRU) is; implemented, and state transition probability and length penalty are; employed in decoding to improve the accuracy. Experimental results show; that proposed model achieves higher F1 score than traditional methods.
 
Citation
北京大学学报. 自然科学版,2017,(2):255-261
URI
https://dspace.xmu.edu.cn/handle/2288/164718

copyright © 2002-2016  Duraspace  Theme by @mire  厦门大学图书馆  
About | Policies
 

 

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

LoginRegister

copyright © 2002-2016  Duraspace  Theme by @mire  厦门大学图书馆  
About | Policies