Research of text classification based on convolution recursive model
In recent years, convolutional neural networks(CNN) and recurrent neural networks(RNN) have been widely used in the field of text classification. In this paper, a model of CNN and long short term memory network(LSTM) feature fusion is proposed. Long-term dependence is obtained by replacing the LSTM...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | zho |
Published: |
National Computer System Engineering Research Institute of China
2019-10-01
|
Series: | Dianzi Jishu Yingyong |
Subjects: | |
Online Access: | http://www.chinaaet.com/article/3000109172 |
id |
doaj-dbc7ee876f2a49d89ee62cee15f4df10 |
---|---|
record_format |
Article |
spelling |
doaj-dbc7ee876f2a49d89ee62cee15f4df102020-11-24T21:51:05ZzhoNational Computer System Engineering Research Institute of ChinaDianzi Jishu Yingyong0258-79982019-10-014510293210.16157/j.issn.0258-7998.1902483000109172Research of text classification based on convolution recursive modelYin Xiaoyu0Alimjan Aysa1Kurban Ubul2School of Information Science & Engineering,Xinjiang University,Urumqi 830046,ChinaSchool of Information Science & Engineering,Xinjiang University,Urumqi 830046,ChinaSchool of Information Science & Engineering,Xinjiang University,Urumqi 830046,ChinaIn recent years, convolutional neural networks(CNN) and recurrent neural networks(RNN) have been widely used in the field of text classification. In this paper, a model of CNN and long short term memory network(LSTM) feature fusion is proposed. Long-term dependence is obtained by replacing the LSTM as a pooling layer, so as to construct a joint CNN and RNN framework to overcome the single convolutional nerve. The network ignores the problem of semantic and grammatical information in the context of words. The proposed method plays an important role in reducing the number of parameters and taking into account the global characteristics of text sequences. The experimental results show that we can achieve the same level of classification performance through a smaller framework, and it can surpass several other methods of the same type in terms of accuracy.http://www.chinaaet.com/article/3000109172text classificationconvolutional neural networkrecurrent neural networkglobal character |
collection |
DOAJ |
language |
zho |
format |
Article |
sources |
DOAJ |
author |
Yin Xiaoyu Alimjan Aysa Kurban Ubul |
spellingShingle |
Yin Xiaoyu Alimjan Aysa Kurban Ubul Research of text classification based on convolution recursive model Dianzi Jishu Yingyong text classification convolutional neural network recurrent neural network global character |
author_facet |
Yin Xiaoyu Alimjan Aysa Kurban Ubul |
author_sort |
Yin Xiaoyu |
title |
Research of text classification based on convolution recursive model |
title_short |
Research of text classification based on convolution recursive model |
title_full |
Research of text classification based on convolution recursive model |
title_fullStr |
Research of text classification based on convolution recursive model |
title_full_unstemmed |
Research of text classification based on convolution recursive model |
title_sort |
research of text classification based on convolution recursive model |
publisher |
National Computer System Engineering Research Institute of China |
series |
Dianzi Jishu Yingyong |
issn |
0258-7998 |
publishDate |
2019-10-01 |
description |
In recent years, convolutional neural networks(CNN) and recurrent neural networks(RNN) have been widely used in the field of text classification. In this paper, a model of CNN and long short term memory network(LSTM) feature fusion is proposed. Long-term dependence is obtained by replacing the LSTM as a pooling layer, so as to construct a joint CNN and RNN framework to overcome the single convolutional nerve. The network ignores the problem of semantic and grammatical information in the context of words. The proposed method plays an important role in reducing the number of parameters and taking into account the global characteristics of text sequences. The experimental results show that we can achieve the same level of classification performance through a smaller framework, and it can surpass several other methods of the same type in terms of accuracy. |
topic |
text classification convolutional neural network recurrent neural network global character |
url |
http://www.chinaaet.com/article/3000109172 |
work_keys_str_mv |
AT yinxiaoyu researchoftextclassificationbasedonconvolutionrecursivemodel AT alimjanaysa researchoftextclassificationbasedonconvolutionrecursivemodel AT kurbanubul researchoftextclassificationbasedonconvolutionrecursivemodel |
_version_ |
1725880532887142400 |