Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (8): 2396-2405.DOI: 10.11772/j.issn.1001-9081.2022071071
Special Issue: 人工智能
• Artificial intelligence • Previous Articles Next Articles
Yumeng CUI, Jingya WANG, Xiaowen LIU, Shangyi YAN, Zhizhong TAO
Received:
2022-07-23
Revised:
2022-09-24
Accepted:
2022-09-28
Online:
2023-01-15
Published:
2023-08-10
Contact:
Jingya WANG
About author:
CUI Yumeng, born in 1998, M. S. candidate. His research interests include named entity recognition, text classification.Supported by:
崔雨萌, 王靖亚, 刘晓文, 闫尚义, 陶知众
通讯作者:
王靖亚
作者简介:
崔雨萌(1998—),男,吉林长春人,硕士研究生,CCF会员,主要研究方向:命名实体识别、文本分类基金资助:
CLC Number:
Yumeng CUI, Jingya WANG, Xiaowen LIU, Shangyi YAN, Zhizhong TAO. General text classification model combining attention and cropping mechanism[J]. Journal of Computer Applications, 2023, 43(8): 2396-2405.
崔雨萌, 王靖亚, 刘晓文, 闫尚义, 陶知众. 融合注意力和裁剪机制的通用文本分类模型[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2396-2405.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2022071071
数据集名称 | 类数 | 文本数 | ||
---|---|---|---|---|
训练集 | 测试集 | 验证集 | ||
复旦大学 | 20 | 15 708 | 1 969 | 1 959 |
搜狗新闻 | 10 | 2 400 | 300 | 300 |
THUCNews | 10 | 180 000 | 10 000 | 10 000 |
今日头条 | 15 | 102 027 | 12 736 | 12 740 |
混合长文本 | 7 | 9 255 | 1 159 | 1 157 |
混合短文本 | 7 | 9 978 | 1 243 | 1 243 |
Tab. 1 Datasets division
数据集名称 | 类数 | 文本数 | ||
---|---|---|---|---|
训练集 | 测试集 | 验证集 | ||
复旦大学 | 20 | 15 708 | 1 969 | 1 959 |
搜狗新闻 | 10 | 2 400 | 300 | 300 |
THUCNews | 10 | 180 000 | 10 000 | 10 000 |
今日头条 | 15 | 102 027 | 12 736 | 12 740 |
混合长文本 | 7 | 9 255 | 1 159 | 1 157 |
混合短文本 | 7 | 9 978 | 1 243 | 1 243 |
部分 | 名称 | 值 |
---|---|---|
BERT | 隐藏层层数(Hidden Layers) | 12 |
隐藏层维度(Hidden Size) | 768 | |
注意力头数(Attention Heads) | 12 | |
文本长度(Text Length) | 32/480 (短文本/长文本) | |
TextCNN | 卷积核尺寸(Filter Size) | (1, 3, 5) |
卷积核数(Number of Filters) | (70, 70, 70) | |
批处理大小(Batch Size) | 128/7 (短文本/长文本) | |
激活函数(Activation Function) | PReLU | |
BiLSTM | 隐藏层层数(Hidden Layers) | 64 |
激活函数(Activation Function) | PReLU | |
DCATT 卷积通道 | 卷积核尺寸(Filter Size) | 3 |
卷积核数(Number of Filters) | 100/1 (编码层/解码层) | |
激活函数(Activation Function) | ReLU | |
DCATT 循环通道 | 隐藏层层数(Hidden Layers) | 1 |
激活函数(Activation Function) | Tanh |
Tab. 2 Parameter setting of models
部分 | 名称 | 值 |
---|---|---|
BERT | 隐藏层层数(Hidden Layers) | 12 |
隐藏层维度(Hidden Size) | 768 | |
注意力头数(Attention Heads) | 12 | |
文本长度(Text Length) | 32/480 (短文本/长文本) | |
TextCNN | 卷积核尺寸(Filter Size) | (1, 3, 5) |
卷积核数(Number of Filters) | (70, 70, 70) | |
批处理大小(Batch Size) | 128/7 (短文本/长文本) | |
激活函数(Activation Function) | PReLU | |
BiLSTM | 隐藏层层数(Hidden Layers) | 64 |
激活函数(Activation Function) | PReLU | |
DCATT 卷积通道 | 卷积核尺寸(Filter Size) | 3 |
卷积核数(Number of Filters) | 100/1 (编码层/解码层) | |
激活函数(Activation Function) | ReLU | |
DCATT 循环通道 | 隐藏层层数(Hidden Layers) | 1 |
激活函数(Activation Function) | Tanh |
模型 | 复旦大学 | 搜狗新闻 | THUCNews | 今日头条 | ||||
---|---|---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
TextCNN[ | 93.65 | 93.13 | 81.00 | 81.30 | 90.16 | 90.16 | 80.73 | 80.67 |
BiLSTM[ | 93.19 | 93.05 | 70.67 | 70.53 | 90.96 | 90.96 | 79.38 | 79.33 |
RCNN[ | 95.83 | 95.55 | 81.33 | 81.57 | 90.89 | 90.89 | 79.99 | 79.99 |
TextCNN-BiLSTM[ | 93.90 | 93.65 | 31.00 | 32.05 | 91.49 | 91.48 | 80.18 | 80.16 |
TextCNN-Attention | 90.24 | 89.43 | 77.18 | 68.64 | 87.86 | 87.86 | 77.18 | 77.09 |
BiLSTM-Attention[ | 92.12 | 91.79 | 75.33 | 74.67 | 83.21 | 83.07 | 76.67 | 76.62 |
TextCNN-BiLSTM-Attention | 96.09 | 96.16 | 76.67 | 75.56 | 91.21 | 91.22 | 79.90 | 79.89 |
BERT[ | 96.19 | 96.13 | 82.33 | 82.15 | 94.27 | 94.27 | 84.96 | 84.85 |
GLSTCM-HNN | 97.15 | 96.86 | 88.00 | 88.01 | 94.43 | 94.42 | 85.23 | 85.16 |
Tab. 3 Comparison of experiment results of different models
模型 | 复旦大学 | 搜狗新闻 | THUCNews | 今日头条 | ||||
---|---|---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
TextCNN[ | 93.65 | 93.13 | 81.00 | 81.30 | 90.16 | 90.16 | 80.73 | 80.67 |
BiLSTM[ | 93.19 | 93.05 | 70.67 | 70.53 | 90.96 | 90.96 | 79.38 | 79.33 |
RCNN[ | 95.83 | 95.55 | 81.33 | 81.57 | 90.89 | 90.89 | 79.99 | 79.99 |
TextCNN-BiLSTM[ | 93.90 | 93.65 | 31.00 | 32.05 | 91.49 | 91.48 | 80.18 | 80.16 |
TextCNN-Attention | 90.24 | 89.43 | 77.18 | 68.64 | 87.86 | 87.86 | 77.18 | 77.09 |
BiLSTM-Attention[ | 92.12 | 91.79 | 75.33 | 74.67 | 83.21 | 83.07 | 76.67 | 76.62 |
TextCNN-BiLSTM-Attention | 96.09 | 96.16 | 76.67 | 75.56 | 91.21 | 91.22 | 79.90 | 79.89 |
BERT[ | 96.19 | 96.13 | 82.33 | 82.15 | 94.27 | 94.27 | 84.96 | 84.85 |
GLSTCM-HNN | 97.15 | 96.86 | 88.00 | 88.01 | 94.43 | 94.42 | 85.23 | 85.16 |
模型 | 复旦大学 | 搜狗新闻 | THUCNews | 今日头条 | ||||
---|---|---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
模型1(BERT-TextCNN[ | 96.19 | 95.28 | 84.00 | 84.14 | 93.81 | 93.81 | 84.81 | 84.74 |
模型2(BERT-TextCNN-BiLSTM) | 96.49 | 96.18 | 86.00 | 86.24 | 93.91 | 93.91 | 85.02 | 84.90 |
模型3(BERT-TextCNN-BiLSTM-DCATT) | 96.59 | 96.44 | 87.33 | 87.26 | — | — | — | — |
本文模型(GLSTCM-HNN) | 97.15 | 96.86 | 88.00 | 88.01 | 94.43 | 94.42 | 85.23 | 85.16 |
Tab. 4 Ablation experimental results
模型 | 复旦大学 | 搜狗新闻 | THUCNews | 今日头条 | ||||
---|---|---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
模型1(BERT-TextCNN[ | 96.19 | 95.28 | 84.00 | 84.14 | 93.81 | 93.81 | 84.81 | 84.74 |
模型2(BERT-TextCNN-BiLSTM) | 96.49 | 96.18 | 86.00 | 86.24 | 93.91 | 93.91 | 85.02 | 84.90 |
模型3(BERT-TextCNN-BiLSTM-DCATT) | 96.59 | 96.44 | 87.33 | 87.26 | — | — | — | — |
本文模型(GLSTCM-HNN) | 97.15 | 96.86 | 88.00 | 88.01 | 94.43 | 94.42 | 85.23 | 85.16 |
类别 | 混合长文本 | 混合短文本 | 混合测试集 | ||||
---|---|---|---|---|---|---|---|
训练集 | 验证集 | 测试集 | 训练集 | 验证集 | 测试集 | ||
总计 | 9 255 | 1 157 | 1 159 | 9 978 | 1 243 | 1 243 | 2 402 |
财经 | 2 800 | 350 | 351 | 2 110 | 263 | 263 | 614 |
汽车 | 240 | 30 | 30 | 867 | 108 | 108 | 138 |
教育 | 336 | 42 | 42 | 2 110 | 263 | 263 | 305 |
体育 | 2 245 | 281 | 281 | 2 364 | 295 | 295 | 576 |
军事 | 360 | 45 | 45 | 605 | 75 | 75 | 120 |
农业 | 1 634 | 204 | 205 | 468 | 58 | 58 | 263 |
政治 | 1 640 | 205 | 205 | 1 454 | 181 | 181 | 386 |
Tab. 5 Distribution of mixed datasets
类别 | 混合长文本 | 混合短文本 | 混合测试集 | ||||
---|---|---|---|---|---|---|---|
训练集 | 验证集 | 测试集 | 训练集 | 验证集 | 测试集 | ||
总计 | 9 255 | 1 157 | 1 159 | 9 978 | 1 243 | 1 243 | 2 402 |
财经 | 2 800 | 350 | 351 | 2 110 | 263 | 263 | 614 |
汽车 | 240 | 30 | 30 | 867 | 108 | 108 | 138 |
教育 | 336 | 42 | 42 | 2 110 | 263 | 263 | 305 |
体育 | 2 245 | 281 | 281 | 2 364 | 295 | 295 | 576 |
军事 | 360 | 45 | 45 | 605 | 75 | 75 | 120 |
农业 | 1 634 | 204 | 205 | 468 | 58 | 58 | 263 |
政治 | 1 640 | 205 | 205 | 1 454 | 181 | 181 | 386 |
模型 | 长文本测试 | 短文本测试 | 混合测试 | |||
---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | |
BERT-TextCNN[ | 95.30 | 95.26 | 78.06 | 77.82 | 86.38 | 86.24 |
BERT-BiLSTM | 89.86 | 89.93 | 75.89 | 75.41 | 82.63 | 82.42 |
BERT-TextCNN-BiLSTM | 91.07 | 91.24 | 76.21 | 76.19 | 83.38 | 83.45 |
CBLGA[ | 63.59 | 54.92 | 57.44 | 48.47 | 60.41 | 51.58 |
GLSTCM⁃HNN | 95.64 | 95.56 | 82.20 | 82.50 | 88.68 | 88.80 |
Tab. 6 Experimental results on each test set after long text training
模型 | 长文本测试 | 短文本测试 | 混合测试 | |||
---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | |
BERT-TextCNN[ | 95.30 | 95.26 | 78.06 | 77.82 | 86.38 | 86.24 |
BERT-BiLSTM | 89.86 | 89.93 | 75.89 | 75.41 | 82.63 | 82.42 |
BERT-TextCNN-BiLSTM | 91.07 | 91.24 | 76.21 | 76.19 | 83.38 | 83.45 |
CBLGA[ | 63.59 | 54.92 | 57.44 | 48.47 | 60.41 | 51.58 |
GLSTCM⁃HNN | 95.64 | 95.56 | 82.20 | 82.50 | 88.68 | 88.80 |
模型 | 长文本测试 | 短文本测试 | 混合测试 | |||
---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | |
BERT-TextCNN[ | 79.34 | 79.30 | 91.49 | 91.55 | 85.63 | 85.64 |
BERT-BiLSTM | 75.63 | 74.81 | 89.97 | 90.08 | 83.05 | 82.71 |
BERT-TextCNN-BiLSTM | 74.42 | 73.88 | 89.72 | 89.92 | 82.34 | 82.18 |
CBLGA[ | 74.37 | 74.01 | 89.06 | 89.19 | 81.97 | 81.87 |
GLSTCM⁃HNN | 83.73 | 84.30 | 92.42 | 92.41 | 88.23 | 88.50 |
Tab. 7 Experimental results on each test set after short text training
模型 | 长文本测试 | 短文本测试 | 混合测试 | |||
---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | |
BERT-TextCNN[ | 79.34 | 79.30 | 91.49 | 91.55 | 85.63 | 85.64 |
BERT-BiLSTM | 75.63 | 74.81 | 89.97 | 90.08 | 83.05 | 82.71 |
BERT-TextCNN-BiLSTM | 74.42 | 73.88 | 89.72 | 89.92 | 82.34 | 82.18 |
CBLGA[ | 74.37 | 74.01 | 89.06 | 89.19 | 81.97 | 81.87 |
GLSTCM⁃HNN | 83.73 | 84.30 | 92.42 | 92.41 | 88.23 | 88.50 |
模型 | 财经 | 汽车 | 教育 | 体育 | 军事 | 农业 | 政治 | 加权平均 |
---|---|---|---|---|---|---|---|---|
BERT-TextCNN[ | 88.35 | 81.83 | 83.62 | 89.83 | 72.00 | 89.81 | 83.13 | 86.24 |
BERT-BiLSTM | 82.51 | 81.35 | 86.91 | 93.13 | 67.06 | 83.47 | 67.19 | 82.42 |
BERT-TextCNN-BiLSTM | 83.06 | 82.50 | 83.06 | 82.50 | 82.75 | 95.75 | 69.54 | 84.94 |
CBLGA[ | 60.55 | 68.24 | 0.00 | 81.17 | 39.27 | 83.36 | 10.14 | 51.58 |
GLSTCM⁃HNN | 91.66 | 86.67 | 85.87 | 93.50 | 71.28 | 91.58 | 83.86 | 88.80 |
Tab. 8 Experimental results on each label in test set after long text training
模型 | 财经 | 汽车 | 教育 | 体育 | 军事 | 农业 | 政治 | 加权平均 |
---|---|---|---|---|---|---|---|---|
BERT-TextCNN[ | 88.35 | 81.83 | 83.62 | 89.83 | 72.00 | 89.81 | 83.13 | 86.24 |
BERT-BiLSTM | 82.51 | 81.35 | 86.91 | 93.13 | 67.06 | 83.47 | 67.19 | 82.42 |
BERT-TextCNN-BiLSTM | 83.06 | 82.50 | 83.06 | 82.50 | 82.75 | 95.75 | 69.54 | 84.94 |
CBLGA[ | 60.55 | 68.24 | 0.00 | 81.17 | 39.27 | 83.36 | 10.14 | 51.58 |
GLSTCM⁃HNN | 91.66 | 86.67 | 85.87 | 93.50 | 71.28 | 91.58 | 83.86 | 88.80 |
模型 | 财经 | 汽车 | 教育 | 体育 | 军事 | 农业 | 政治 | 加权平均 |
---|---|---|---|---|---|---|---|---|
BERT-TextCNN[ | 86.06 | 87.31 | 86.00 | 94.61 | 78.82 | 86.39 | 72.31 | 85.64 |
BERT-BiLSTM | 84.58 | 84.72 | 86.74 | 93.52 | 66.87 | 87.69 | 61.25 | 82.72 |
BERT-TextCNN-BiLSTM | 83.87 | 82.53 | 84.21 | 95.45 | 71.68 | 83.14 | 60.59 | 82.18 |
CBLGA[ | 82.55 | 81.72 | 89.33 | 91.99 | 64.65 | 83.69 | 63.93 | 81.87 |
GLSTCM⁃HNN | 87.39 | 87.55 | 87.72 | 95.26 | 79.18 | 91.18 | 82.19 | 88.50 |
Tab. 9 Experimental results on each label in test set after short text training
模型 | 财经 | 汽车 | 教育 | 体育 | 军事 | 农业 | 政治 | 加权平均 |
---|---|---|---|---|---|---|---|---|
BERT-TextCNN[ | 86.06 | 87.31 | 86.00 | 94.61 | 78.82 | 86.39 | 72.31 | 85.64 |
BERT-BiLSTM | 84.58 | 84.72 | 86.74 | 93.52 | 66.87 | 87.69 | 61.25 | 82.72 |
BERT-TextCNN-BiLSTM | 83.87 | 82.53 | 84.21 | 95.45 | 71.68 | 83.14 | 60.59 | 82.18 |
CBLGA[ | 82.55 | 81.72 | 89.33 | 91.99 | 64.65 | 83.69 | 63.93 | 81.87 |
GLSTCM⁃HNN | 87.39 | 87.55 | 87.72 | 95.26 | 79.18 | 91.18 | 82.19 | 88.50 |
1 | LIU G, GUO J B. Bidirectional LSTM with attention mechanism and convolutional layer for text classification[J]. Neurocomputing, 2019, 337: 325-338. 10.1016/j.neucom.2019.01.078 |
2 | 谢金宝,李嘉辉,康守强,等. 基于循环卷积多任务学习的多领域文本分类方法[J]. 电子与信息学报, 2021, 43(8):2395-2403. 10.11999/JEIT200869 |
XIE J B, LI J H, KANG S Q, et al. A multi-domain text classification method based on recurrent convolution multi-task learning[J]. Journal of Electronics and Information Technology, 2021, 43(8): 2395-2403. 10.11999/JEIT200869 | |
3 | WATANABE A, SASANO R, TAKAMURA H, et al. Generating personalized snippets for web page recommender systems[C]// Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technologies - Volume 2. Piscataway: IEEE, 2014: 218-225. 10.1109/wi-iat.2014.101 |
4 | TAI K S, SOCHER R, MANNING C D. Improved semantic representations from tree-structured long short-term memory networks[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2015: 1556-1566. 10.3115/v1/p15-1150 |
5 | ZHU X D, SOBIHANI P, GUO H Y. Long short-term memory over recursive structures[C]// Proceedings of the 32nd International Conference on Machine Learning. New York: JMLR.org, 2015: 1604-1612. |
6 | D’ANDREA E, DUCANGE P, BECHINI A, et al. Monitoring the public opinion about the vaccination topic from tweets analysis[J]. Expert Systems with Applications, 2019, 116: 209-226. 10.1016/j.eswa.2018.09.009 |
7 | DESMET B, HOSTE V. Online suicide prevention through optimised text classification[J]. Information Sciences, 2018, 439/440: 61-78. 10.1016/j.ins.2018.02.014 |
8 | PEREIRA-KOHATSU J C, QUIJANO-SÁNCHEZ L, LIBERATORE F, et al. Detecting and monitoring hate speech in Twitter[J]. Sensors, 2019, 19(21): No.4654. 10.3390/s19214654 |
9 | LI C B, ZHAN G H, LI Z H. News text classification based on improved Bi-LSTM-CNN[C]// Proceedings of the 9th International Conference on Information Technology in Medicine and Education. Piscataway: IEEE, 2018: 890-893. 10.1109/itme.2018.00199 |
10 | PENG F C, SCHUURMANS D. Combining naive Bayes and n-gram language models for text classification[C]// Proceedings of the 2003 European Conference on Information Retrieval, LNCS 2633. Berlin: Springer, 2003: 335-350. |
11 | LI L P, WEINBERG C R, DARDEN T A, et al. Gene selection for sample classification based on gene expression data: study of sensitivity to choice of parameters of the GA/KNN method[J]. Bioinformatics, 2001, 17(12): 1131-1142. 10.1093/bioinformatics/17.12.1131 |
12 | MANEVITZ L M, YOUSEF M. One-class SVMs for document classification[J]. Journal of Machine Learning Research, 2001, 2: 139-154. |
13 | LIU P, ZHAO H H, TENG J Y, et al. Parallel naive Bayes algorithm for large-scale Chinese text classification based on spark[J]. Journal of Central South University, 2019, 26(1): 1-12. 10.1007/s11771-019-3978-x |
14 | KHAMAR K. Short text classification using kNN based on distance function[J]. International Journal of Advanced Research in Computer and Communication Engineering, 2013, 2(4): 1916-1919. |
15 | KIM Y. Convolutional neural networks for sentence classification[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2014:1746-1751. 10.3115/v1/d14-1181 |
16 | ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization[EB/OL]. (2015-02-19) [2022-07-09].. |
17 | CONNEAU A, SCHWENK H, BARRAULT L, et al. Very deep convolutional networks for text classification[C]// Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. Stroudsburg, PA: ACL, 2017: 1107-1116. 10.18653/v1/e17-1104 |
18 | 康雁,李浩,梁文韬,等. 针对文本情感分类任务的textSE-ResNeXt集成模型[J]. 计算机工程与应用, 2020, 56(7):205-209. |
KANG Y, LI H, LIANG W T, et al. textSE-ResNeXt integration model for text sentiment classification tasks[J]. Computer Engineering and Applications, 2020, 56(7): 205-209. | |
19 | YANG W S, LI J Y, FUKUMOTO F, et al. MSCNN: a hybrid-Siamese convolutional neural network for extremely imbalanced multi-label text classification[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2020: 6716-6722. 10.18653/v1/2020.emnlp-main.545 |
20 | KALCHBRENNER N, GREFENSTETTE E, BLUNSOM P. A convolutional neural network for modelling sentences[C]// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2014: 655-665. 10.3115/v1/p14-1062 |
21 | HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. 10.1162/neco.1997.9.8.1735 |
22 | CHUNG J, GULCEHRE C, CHO K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL]. (2014-12-11) [2022-07-10].. 10.1007/978-3-030-89929-5_3 |
23 | SCHUSTER M, PALIWAL K K. Bidirectional recurrent neural networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11): 2673-2681. 10.1109/78.650093 |
24 | XU G X, MENG Y T, QIU X Y, et al. Sentiment analysis of comment texts based on BiLSTM[J]. IEEE Access, 2019, 7: 51522-51532. 10.1109/access.2019.2909919 |
25 | 王伟,孙玉霞,齐庆杰,等. 基于BiGRU-attention神经网络的文本情感分类模型[J]. 计算机应用研究, 2019, 36(12):3558-3564. |
WANG W, SUN Y X, QI Q J, et al. Text sentiment classification model based on BiGRU-attention neural network[J]. Application Research of Computers, 2019, 36(12): 3558-3564. | |
26 | KOWSARI K, JAFARI MEIMANDI K, HEIDARYSAFA M, et al. Text classification algorithms: a survey[J]. Information, 2019, 10(4): No.150. 10.3390/info10040150 |
27 | LAI S W, XU L H, LIU K, et al. Recurrent convolutional neural networks for text classification[C]// Proceedings of the 29th AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2015: 2267-2273. 10.1609/aaai.v29i1.9513 |
28 | 曹梦舟,张艳. 基于卷积-长短期记忆网络的电能质量扰动分类[J]. 电力系统保护与控制, 2020, 48(2):86-92. |
CAO M Z, ZHANG Y. Classification for power quality disturbances based on CNN-LSTM network[J]. Power System Protection and Control, 2020, 48(2): 86-92. | |
29 | LUO L X. Network text sentiment analysis method combining LDA text representation and GRU-CNN[J]. Personal and Ubiquitous Computing, 2019, 23(3/4): 405-412. 10.1007/s00779-018-1183-9 |
30 | LU H B, LIU X B, YIN Y C, et al. A patent text classification model based on multivariate neural network fusion[C]// Proceedings of the 6th International Conference on Soft Computing and Machine Intelligence. Piscataway: IEEE, 2019: 61-65. 10.1109/iscmi47871.2019.9004335 |
31 | 韩永鹏. 面向长短混合场景下的文本分类方法研究[D]. 北京:北京工业大学, 2020:37-51. 10.7498/aps.69.20191162 |
HAN Y P. Research on text classification method in mixed long and short scenes[D]. Beijing: Beijing University of Technology, 2020: 37-51. 10.7498/aps.69.20191162 | |
32 | MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[C]// Proceedings of the 26th International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2013: 3111-3119. |
33 | PENNINGTON J, SOCHER R, MANNING C D. GloVe: global vectors for word representation[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2014: 1532-1543. 10.3115/v1/d14-1162 |
34 | PETERS M E, NEUMANN M, IYYER M, et al. Deep contextualized word representations[C]// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA: ACL, 2018: 2227-2237. 10.18653/v1/n18-1202 |
35 | DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Stroudsburg, PA: ACL, 2019: 4171-4186. 10.18653/v1/n18-2 |
36 | DENG J F, CHENG L L, WANG Z W. Attention-based BiLSTM fused CNN with gating mechanism model for Chinese long text classification[J]. Computer Speech and Language, 2021, 68: No.101182. 10.1016/j.csl.2020.101182 |
37 | YAO L, JIN Z, MAO C S, et al. Traditional Chinese medicine clinical records classification with BERT and domain specific corpora[J]. Journal of the American Medical Informatics Association, 2019, 26(12): 1632-1636. 10.1093/jamia/ocz164 |
38 | 孙红,陈强越. 融合BERT词嵌入和注意力机制的中文文本分类[J].小型微型计算机系统, 2022, 43(1):22-26. 10.3969/j.issn.1000-1220.2022.01.004 |
SUN H, CHEN Q Y. Chinese text classification based on BERT and attention[J]. Journal of Chinese Computer Systems, 2022, 43(1): 22-26. 10.3969/j.issn.1000-1220.2022.01.004 | |
39 | 刘凯洋. 结合Bert字向量和卷积神经网络的新闻文本分类方法[J]. 电脑知识与技术, 2020, 16(1):187-188. |
LIU K Y. A Chinese news text classification method of combining Bert character vector and convolutional neural networks[J]. Computer Knowledge and Technology, 2020, 16(1): 187-188. | |
40 | KASTNER S, UNGERLEIDER L G. Mechanism of visual attention in the human cortex[J]. Annual Review of Neuroscience, 2000, 23: 315-341. 10.1146/annurev.neuro.23.1.315 |
41 | BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[EB/OL]. (2016-05-19) [2022-07-11].. 10.1017/9781108608480.003 |
42 | XIE J B, HOU Y J, WANG Y J, et al. Chinese text classification based on attention mechanism and feature-enhanced fusion neural network[J]. Computing, 2020, 102(3): 683-700. 10.1007/s00607-019-00766-9 |
43 | TAO H Q, TONG S W, ZHAO H K, et al. A radical-aware attention-based model for Chinese text classification[C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2019: 5125-5132. 10.1609/aaai.v33i01.33015125 |
44 | QIAO X, PENG C, LIU Z, et al. Word-character attention model for Chinese text classification[J]. International Journal of Machine Learning and Cybernetics, 2019, 10(12): 3521-3537. 10.1007/s13042-019-00942-5 |
45 | VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2017:6000-6010. |
46 | 复旦大学计算机信息与技术系国际数据库中心自然语言处理小组. 复旦大学中文文本分类数据集[DS/OL]. (2019-07-17) [2022-09-05].. |
Natural Language Processing Group, International Database Center, Department of Computer Information and Technology, Fudan University. Fudan university Chinese text classification dataset[DS/OL]. (2019-07-17) [2022-09-05].. | |
47 | SogouCS.reduced[DS/OL]. [2022-05-29].. |
48 | 清华大学自然语言处理实验室. 中文文本分类数据集THUCNews[DS/OL]. [2022-05-30].http://thuctc.thunlp.org/#中文文本分类数据集THUCNews. |
Natural Language Processing Laboratory of Tsinghua University. Chinese text classification dataset THUCNews[DS/OL]. [2022-05-30]. | |
中文文本分类数据集THUCNews. | |
49 | Aceimnorstuvwxz. 今日头条中文新闻(文本)分类数据集[DS/OL]. [2022-09-06].. |
Aceimnorstuvwxz. Tutiao-text-classification-dataset[DS/OL]. [2022-09-06].. | |
50 | 周志华. 机器学习[M]. 北京:清华大学出版社, 2016:25-26. |
ZHOU Z H. Machine Learning[M]. Beijing: Tsinghua University Press, 2016: 25-26. | |
51 | LIU P F, QIU X P, HUANG X J. Recurrent neural network for text classification with multi-task learning[C]// Proceedings of the 25th International Joint Conference on Artificial Intelligence. California: ijcai.org, 2016: 2873-1879. 10.24963/ijcai.2017/473 |
52 | ZHOU C T, SUN C L, LIU Z Y, et al. A C-LSTM neural network for text classification[EB/OL]. (2015-11-30) [2022-07-11].. |
53 | ZHOU P, SHI W, TIAN J, et al. Attention-based bidirectional long short-term memory networks for relation classification[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Stroudsburg, PA: ACL, 2016: 207-212. 10.18653/v1/p16-2034 |
54 | GUO B, ZHANG C X, LIU J M, et al. Improving text classification with weighted word embeddings via a multi-channel TextCNN model[J]. Neurocomputing, 2019, 363:366-374. 10.1016/j.neucom.2019.07.052 |
55 | 王得强,吴军,王立平. 适于长短文本分类的CBLGA和CBLCA混联模型[J]. 吉林大学学报(信息科学版), 2021, 39(5):553-561. |
WANG D Q, WU J, WANG L P. CBLGA and CBLCA hybrid model for long and short text’s classification[J]. Journal of Jilin University (Information Science Edition), 2021, 39(5): 553-561. |
[1] | Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974. |
[2] | Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918. |
[3] | Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738. |
[4] | Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969. |
[5] | Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877. |
[6] | Zhiqiang ZHAO, Peihong MA, Xinhong HEI. Crowd counting method based on dual attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2886-2892. |
[7] | Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703. |
[8] | Kaipeng XUE, Tao XU, Chunjie LIAO. Multimodal sentiment analysis network with self-supervision and multi-layer cross attention [J]. Journal of Computer Applications, 2024, 44(8): 2387-2392. |
[9] | Pengqi GAO, Heming HUANG, Yonghong FAN. Fusion of coordinate and multi-head attention mechanisms for interactive speech emotion recognition [J]. Journal of Computer Applications, 2024, 44(8): 2400-2406. |
[10] | Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557. |
[11] | Zhonghua LI, Yunqi BAI, Xuejin WANG, Leilei HUANG, Chujun LIN, Shiyu LIAO. Low illumination face detection based on image enhancement [J]. Journal of Computer Applications, 2024, 44(8): 2588-2594. |
[12] | Shangbin MO, Wenjun WANG, Ling DONG, Shengxiang GAO, Zhengtao YU. Single-channel speech enhancement based on multi-channel information aggregation and collaborative decoding [J]. Journal of Computer Applications, 2024, 44(8): 2611-2617. |
[13] | Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625. |
[14] | Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650. |
[15] | Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||