Short Text Classification Based on Explicit and Implicit Multiscale Weighted Semantic Information

被引:1
作者
Gong, Jun [1 ]
Zhang, Juling [2 ]
Guo, Wenqiang [2 ]
Ma, Zhilong [2 ]
Lv, Xiaoyi [3 ]
机构
[1] Xinjiang Univ, Teaching Affairs Div, Urumqi 830046, Peoples R China
[2] Xinjiang Univ Finance & Econ, Sch Cyberspace Secur, Urumqi 830012, Peoples R China
[3] Xinjiang Univ, Sch Software, Urumqi 830046, Peoples R China
来源
SYMMETRY-BASEL | 2023年 / 15卷 / 11期
关键词
convolution neural network; explicit semantics; implicit semantics; recurrent neural network; short text classification; ATTENTION;
D O I
10.3390/sym15112008
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Considering the poor effect of short text classification due to insufficient semantic information mining in the current short text matching methods, a new short text classification method is proposed based on explicit and implicit multiscale weighting semantic information interaction. First, the explicit and implicit representations of short text are obtained by a word vector model (word2vec), convolutional neural networks (CNNs), and long short-term memory (LSTM). Then, a multiscale convolutional neural network obtains the explicit and implicit multiscale weighting semantics information of short text. Finally, the multiscale weighting semantics is fused for more accurate short text classification. The experimental results show that this method is superior to the existing classical short text classification algorithms and two advanced short text classification models on the five short text classification datasets of MR, Subj, TREC, SST1 and SST2 with accuracies of 85.7%, 96.9%, 98.1%, 53.4% and 91.8%, respectively.
引用
收藏
页数:11
相关论文
共 24 条
[1]   Recurrent neural networks for robust real-world text classffication [J].
Arevian, Garen .
PROCEEDINGS OF THE IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON WEB INTELLIGENCE: WI 2007, 2007, :326-329
[2]  
Chen S., 2022, P 2022 IEEE C EV COM, P1
[3]   An intelligent Chatbot using deep learning with Bidirectional RNN and attention model [J].
Dhyani, Manyu ;
Kumar, Rajiv .
MATERIALS TODAY-PROCEEDINGS, 2021, 34 :817-824
[4]   A new mobile convolutional neural network-based approach for pixel-wise road surface crack detection [J].
Dogan, Gurkan ;
Ergen, Burhan .
MEASUREMENT, 2022, 195
[5]  
Hao LD, 2018, 2018 IEEE 3RD INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND BIG DATA ANALYSIS (ICCCBDA), P93, DOI 10.1109/ICCCBDA.2018.8386493
[6]  
Kim Y., 2014, ARXIV
[7]  
Lai S., 2022, P 4 INT C ADV COMP T, P1
[8]   A Cyclical Learning Rate Method in Deep Learning Training [J].
Li, Jiaqi ;
Yang, Xiaodong .
PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON COMPUTER, INFORMATION AND TELECOMMUNICATION SYSTEMS (CITS), 2020, :140-144
[9]  
Parida Upasana, 2019, 2019 International Conference on Applied Machine Learning (ICAML). Proceedings, P165, DOI 10.1109/ICAML48257.2019.00039
[10]  
Prakash S., 2023, 2023 6 INT C INF SYS, P1, DOI DOI 10.1109/ISCON57294.2023.10112065