Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (5): 1461-1466.DOI: 10.11772/j.issn.1001-9081.2022040641
• Artificial intelligence • Previous Articles Next Articles
Senqi YANG1,2, Xuliang DUAN1,2(), Zhan XIAO1,2, Songsong LANG1,2, Zhiyong LI1,2
Received:
2022-05-07
Revised:
2022-07-15
Accepted:
2022-07-22
Online:
2022-08-12
Published:
2023-05-10
Contact:
Xuliang DUAN
About author:
YANG Senqi, born in 1997, M. S. candidate. His research interests include natural language processing.Supported by:
杨森淇1,2, 段旭良1,2(), 肖展1,2, 郎松松1,2, 李志勇1,2
通讯作者:
段旭良
作者简介:
杨森淇(1997—),男,河北廊坊人,硕士研究生,主要研究方向:自然语言处理基金资助:
CLC Number:
Senqi YANG, Xuliang DUAN, Zhan XIAO, Songsong LANG, Zhiyong LI. Text classification of agricultural news based on ERNIE+DPCNN+BiGRU[J]. Journal of Computer Applications, 2023, 43(5): 1461-1466.
杨森淇, 段旭良, 肖展, 郎松松, 李志勇. 基于ERNIE+DPCNN+BiGRU的农业新闻文本分类[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1461-1466.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2022040641
类别 | 训练集 | 测试集 | 验证集 | 总计 | 平均长度 |
---|---|---|---|---|---|
总计 | 12 778 | 1 384 | 1 386 | 15 548 | 18.98 |
渔业 | 2 297 | 258 | 258 | 2 813 | 21.01 |
林业 | 1 936 | 192 | 193 | 2 321 | 19.82 |
种植业 | 3 645 | 356 | 357 | 4 358 | 16.19 |
畜牧业 | 3 239 | 371 | 371 | 3 981 | 17.68 |
副业 | 1 661 | 207 | 207 | 2 075 | 20.20 |
Tab. 1 Number of each category in dataset
类别 | 训练集 | 测试集 | 验证集 | 总计 | 平均长度 |
---|---|---|---|---|---|
总计 | 12 778 | 1 384 | 1 386 | 15 548 | 18.98 |
渔业 | 2 297 | 258 | 258 | 2 813 | 21.01 |
林业 | 1 936 | 192 | 193 | 2 321 | 19.82 |
种植业 | 3 645 | 356 | 357 | 4 358 | 16.19 |
畜牧业 | 3 239 | 371 | 371 | 3 981 | 17.68 |
副业 | 1 661 | 207 | 207 | 2 075 | 20.20 |
模型 | 精确率 | 召回率 | F1分数 |
---|---|---|---|
BERT | 0.673 8 | 0.684 2 | 0.655 4 |
RoBERTa | 0.628 9 | 0.550 3 | 0.476 4 |
MacBERT | 0.671 4 | 0.682 7 | 0.665 1 |
BERT+CNN | 0.705 1 | 0.720 6 | 0.638 8 |
BERT+BiGRU | 0.691 6 | 0.694 1 | 0.690 9 |
BERT+DPCNN | 0.686 8 | 0.691 8 | 0.668 8 |
ERNIE | 0.883 8 | 0.880 0 | 0.879 3 |
ERNIE+DPCNN | 0.883 1 | 0.880 0 | 0.878 7 |
ERNIE+BiGRU | |||
EGC | 0.898 5 | 0.892 9 | 0.893 5 |
Tab. 2 Comparison of weighted-average indicators of different models
模型 | 精确率 | 召回率 | F1分数 |
---|---|---|---|
BERT | 0.673 8 | 0.684 2 | 0.655 4 |
RoBERTa | 0.628 9 | 0.550 3 | 0.476 4 |
MacBERT | 0.671 4 | 0.682 7 | 0.665 1 |
BERT+CNN | 0.705 1 | 0.720 6 | 0.638 8 |
BERT+BiGRU | 0.691 6 | 0.694 1 | 0.690 9 |
BERT+DPCNN | 0.686 8 | 0.691 8 | 0.668 8 |
ERNIE | 0.883 8 | 0.880 0 | 0.879 3 |
ERNIE+DPCNN | 0.883 1 | 0.880 0 | 0.878 7 |
ERNIE+BiGRU | |||
EGC | 0.898 5 | 0.892 9 | 0.893 5 |
激活函数 | F1分数 | 权重平均 | ||||
---|---|---|---|---|---|---|
渔业 | 林业 | 种植业 | 畜牧业 | 副业 | ||
ReLU | 0.873 1 | 0.905 1 | 0.885 8 | 0.946 6 | 0.770 0 | 0.893 5 |
Leaky ReLU | 0.881 6 | 0.962 5 | 0.887 5 | 0.947 9 | 0.809 8 | 0.902 9 |
RReLU | 0.877 8 | 0.932 2 | 0.888 6 | 0.948 9 | 0.807 8 | 0.903 4 |
PReLU | 0.871 3 | 0.922 1 | 0.877 1 | 0.945 2 | 0.788 2 | 0.894 6 |
Tab. 3 Performance comparison of four different activation functions
激活函数 | F1分数 | 权重平均 | ||||
---|---|---|---|---|---|---|
渔业 | 林业 | 种植业 | 畜牧业 | 副业 | ||
ReLU | 0.873 1 | 0.905 1 | 0.885 8 | 0.946 6 | 0.770 0 | 0.893 5 |
Leaky ReLU | 0.881 6 | 0.962 5 | 0.887 5 | 0.947 9 | 0.809 8 | 0.902 9 |
RReLU | 0.877 8 | 0.932 2 | 0.888 6 | 0.948 9 | 0.807 8 | 0.903 4 |
PReLU | 0.871 3 | 0.922 1 | 0.877 1 | 0.945 2 | 0.788 2 | 0.894 6 |
1 | 景丽,何婷婷. 基于改进TF-IDF和ABLCNN的中文文本分类模型[J]. 计算机科学, 2021, 48(11A):170-175, 190. 10.11896/jsjkx.210100232 |
JING L, HE T T. Chinese text classification model based on improved TF-IDF and ABLCNN[J]. Computer Science, 2021, 48(11A):170-175, 190. 10.11896/jsjkx.210100232 | |
2 | WANG K, HAN S C, POON J. InducT-GCN: inductive graph convolutional networks for text classification[EB/OL]. [2022-02-08]. . 10.1109/icpr56361.2022.9956075 |
3 | WANG K Z, HAN S C, LONG S Q, et al. ME-GCN: multi-dimensional edge-embedded graph convolutional networks for semi-supervised text classification[EB/OL]. [2022-04-23]. . |
4 | YANG C H H, QI J, CHEN S Y C, et al. When BERT meets quantum temporal convolution learning for text classification in heterogeneous computing[C]// Proceeding of the 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing. Piscataway: IEEE, 2022: 8602-8606. 10.1109/icassp43922.2022.9746412 |
5 | 薛春香,张玉芳. 面向新闻领域的中文文本分类研究综述[J]. 图书情报工作, 2013, 57(14):134-139. 10.7536/j.issn.0252-3116.2013.14.022 |
XUE C X, ZHANG Y F. Research review on chinese text classification in the news field[J]. Library and Information Service, 2013, 57(14): 134-139. 10.7536/j.issn.0252-3116.2013.14.022 | |
6 | 谢志峰,吴佳萍,马利庄. 基于卷积神经网络的中文财经新闻分类方法[J]. 山东大学学报(工学版), 2018, 48(3): 34-39, 66. 10.6040/j.issn.1672-3961.0.2017.433 |
XIE Z F, WU J P, MA L Z. Chinese financial news classification method based on convolutional neural network[J]. Journal of Shandong University (Engineering Science), 2018, 48(3): 34-39, 66. 10.6040/j.issn.1672-3961.0.2017.433 | |
7 | 许英姿,任俊玲. 基于改进的加权补集朴素贝叶斯物流新闻[J]. 计算机工程与设计, 2022, 43(1): 179-185. |
XU Y Z, REN J L. Naive Bayesian logistics news classification based on improved weighted complement[J]. Computer Engineering and Design, 2022, 43(1): 179-185. | |
8 | 朱芳鹏,王晓峰. 面向船舶工业新闻的文本分类[J]. 电子测量与仪器学报, 2020, 34(1):149-155. |
ZHU F P, WANG X F. Text classification for ship industry news[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34(1):149-155. | |
9 | 李超凡,马凯. 基于注意力机制结合CNN-BiLSTM模型的电子病历文本分类[J]. 科学技术与工程, 2022, 22(6):2363-2370. 10.3969/j.issn.1671-1815.2022.06.028 |
LI C F, MA K. Electronic medical record text classification based on attention mechanism combined with CNN-BiLSTM[J]. Science Technology and Engineering, 2022, 22(6): 2363-2370. 10.3969/j.issn.1671-1815.2022.06.028 | |
10 | 霍婷婷. 基于fastText的新闻文本分类研究及在农业新闻中的应用[D]. 长春:吉林大学, 2019:1-3. |
HUO T T. Research on fastText-based classification of news texts and its application in agricultural news[D]. Changchun: Jilin University, 2019:1-3 | |
11 | 金宁,赵春江,吴华瑞,等. 基于BiGRU_MulCNN的农业问答问句分类技术研究[J]. 农业机械学报, 2020, 51(5):199-206. 10.6041/j.issn.1000-1298.2020.05.022 |
JIN N, ZHAO C J, WU H R, et al. Classification technology of agricultural questions based on BiGRU_MulCNN[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(5): 199-206. 10.6041/j.issn.1000-1298.2020.05.022 | |
12 | 王郝日钦,吴华瑞,冯帅,等. 基于Attention_DenseCNN的水稻问答系统问句分类[J]. 农业机械学报, 2021, 52(7):237-243. 10.6041/j.issn.1000-1298.2021.07.025 |
WANG H R Q, WU H R, FENG S, et al. Classification technology of rice questions in question answering system based on Attention_DenseCNN[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(7): 237-243. 10.6041/j.issn.1000-1298.2021.07.025 | |
13 | LIU Y H,OTT M, GOYAL N, et al. RoBERTa: a robustly optimized BERT pretraining approach[EB/OL]. (2019-07-26) [2022-04-24].. |
14 | CUI Y M, CHE W X, LIU T, et al. Revisiting pre-trained models for Chinese natural language processing[C]// Findings of the Association for Computational Linguistics: EMNLP 2020. Stroudsburg, PA: ACL, 2020: 657-668. 10.18653/v1/2020.findings-emnlp.58 |
15 | 杨先凤,赵家和,李自强. 融合字注释的文本分类模型[J]. 计算机应用, 2022, 42(5):1317-1323. 10.11772/j.issn.1001-9081.2021030489 |
YANG X F, ZHAO J H, LI Z Q. Text classification model combining word annotations[J]. Journal of Computer Applications, 2022, 42(5):1317-1323. 10.11772/j.issn.1001-9081.2021030489 | |
16 | 彭玉芳,石进,徐浩,等. 基于BERT和分面分类的多标签的南海证据性数据分类研究[J]. 图书馆杂志, 2022, 41(5):102-108. |
PENG Y F, SHI J, XU H, et al. Research on multi-label evidence data of the South China Sea classification based on BERT and faceted classification[J]. Library Journal, 2022, 41(5): 102-108. | |
17 | 张海丰,曾诚,潘列,等. 结合BERT和特征投影网络的新闻主题文本分类方法[J]. 计算机应用, 2022, 42(4):1116-1124. |
ZHANG H F, ZENG C, PAN L, et al. News topic text classification method based on BERT and feature projection network[J]. Journal of Computer Applications, 2022, 42(4): 1116-1124. | |
18 | CUI Y M, CHE W X, LIU T, et al. Pre-training with whole word masking for Chinese BERT[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 29: 3504-3514. 10.1109/taslp.2021.3124365 |
19 | SUN Y, WANG S H, LI Y K, et al. ERNIE: enhanced representation through knowledge integration[EB/OL]. (2019-04-19) [2022-04-24].. |
20 | 陈杰,马静,李晓峰. 融合预训练模型文本特征的短文本分类方法[J]. 数据分析与知识发现, 2021, 5(9):21-30. |
CHEN J, MA J, LI X F. Short-text classification method with text features from pre-trained models[J]. Data Analysis and Knowledge Discovery, 2021, 5(9):21-30. | |
21 | 黄山成,韩东红,乔百友,等. 基于ERNIE2.0-BiLSTM-Attention的隐式情感分析方法[J]. 小型微型计算机系统, 2021, 42(12):2485-2489. |
HUANG S C, HAN D H, QIAO B Y, et al. Implicit sentiment analysis method based on ERNIE2.0-BiLSTM-Attention[J]. Journal of Chinese Computer Systems, 2021, 42(12):2485-2489. | |
22 | 喻航,李红莲,吕学强. 人大报告内容的文本分类[J]. 计算机工程与设计, 2021, 42(6):1772-1778. 10.16208/j.issn1000-7024.2021.06.036 |
YU H, LI H L, LYU X Q. Text classification of NPC report contents[J]. Computer Engineering and Design, 2021, 42(6): 1772-1778. 10.16208/j.issn1000-7024.2021.06.036 | |
23 | 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. |
24 | HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780. 10.1162/neco.1997.9.8.1735 |
25 | CHO K, van MERRIËNBOER B, GU̇LÇEHRE Ç, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2014: 1724-1734. 10.3115/v1/d14-1179 |
26 | JOHNSON R, ZHANG T. Deep pyramid convolutional neural networks for text categorization[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2017: 562-570. 10.18653/v1/p17-1052 |
27 | 沈彬,严馨,周丽华,等. 基于ERNIE和双重注意力机制的微博情感分析[J]. 云南大学学报(自然科学版), 2022, 44(3): 480-489. |
SHEN B, YAN X, ZHOU L H, et al. Microblog sentiment analysis based on ERNIE and dual attention mechanism[J]. Journal of Yunnan University (Natural Science Edition), 2022, 44(3): 480-489. | |
28 | 崔玉洁,廖坤. 借助八爪鱼采集器实现过刊网刊元数据的自动提取[J]. 编辑学报, 2016, 28(5): 485-488. |
CUI Y J, LIAO K. Realization of automatic extraction of metadata in back issues of network journals by octopus collector[J]. Acta Editologica, 2016, 28(5): 485-488. | |
29 | 李默涵,李建中. 数据时效性判定:关键理论和技术[J]. 智能计算机与应用, 2016, 6(6):72-75. 10.3969/j.issn.2095-2163.2016.06.020 |
LI M H, LI J Z. Data currency determination: key theories and technologies[J]. Intelligent Computer and Applications, 2016, 6(6): 72-75. 10.3969/j.issn.2095-2163.2016.06.020 | |
30 | 李建中,刘显敏. 大数据的一个重要方面:数据可用性[J]. 计算机研究与发展, 2013, 50(6):1147-1162. 10.7544/issn1000-1239.2013.20130646 |
LI J Z, LIU X M. An important aspect of big data: data usability[J]. Journal of Computer Research and Development, 2013, 50(6): 1147-1162. 10.7544/issn1000-1239.2013.20130646 | |
31 | 段旭良,郭兵,沈艳,等. 基于时效规则的数据修复方法[J]. 软件学报, 2019, 30(3):589-603. |
DUAN X L, GUO B, SHEN Y, et al. Data repair algorithm based on currency rules[J]. Journal of Software, 2019, 30(3): 589-603. | |
32 | BERGER A, GUDA S. Threshold optimization for F measure of macro-averaged precision and recall[J]. Pattern Recognition, 2020, 102: No.107250. 10.1016/j.patcog.2020.107250 |
33 | LIU M, CAI Z Q, CHEN J S. Adaptive two-layer ReLU neural network: I. best least-squares approximation[J]. Computers and Mathematics with Applications, 2022, 113: 34-44. 10.1016/j.camwa.2022.03.005 |
34 | MANIATOPOULOS A, MITIANOUDIS N. Learnable Leaky ReLU (LeLeLU): an alternative accuracy-optimized activation function[J]. Information, 2021, 12(12): No.513. 10.3390/info12120513 |
35 | BANERJEE C, MUKHERJEE T, PASILIAO E. Feature representations using the Reflected Rectified Linear Unit (RReLU) activation[J]. Big Data Mining and Analytics, 2020, 3(2):102-120. 10.26599/bdma.2019.9020024 |
36 | NAYEF B H, ABDULLAH S N H S, SULAIMAN R, et al. Optimized leaky ReLU for handwritten Arabic character recognition using convolution neural networks[J]. Multimedia Tools and Applications, 2022, 81(2): 2065-2094. 10.1007/s11042-021-11593-6 |
[1] | Hong CHEN, Bing QI, Haibo JIN, Cong WU, Li’ang ZHANG. Class-imbalanced traffic abnormal detection based on 1D-CNN and BiGRU [J]. Journal of Computer Applications, 2024, 44(8): 2493-2499. |
[2] | Xianfeng YANG, Jiahe ZHAO, Ziqiang LI. Text classification model combining word annotations [J]. Journal of Computer Applications, 2022, 42(5): 1317-1323. |
[3] | LAI Xuemei, TANG Hong, CHEN Hongyu, LI Shanshan. Multimodal sentiment analysis based on feature fusion of attention mechanism-bidirectional gated recurrent unit [J]. Journal of Computer Applications, 2021, 41(5): 1268-1274. |
[4] | WEN Chaodong, ZENG Cheng, REN Junwei, ZHANG Yan. Patent text classification based on ALBERT and bidirectional gated recurrent unit [J]. Journal of Computer Applications, 2021, 41(2): 407-412. |
[5] | CHEN Jie, SHAO Zhiqing, ZHANG Huanhuan, FEI Jiahui. Short text sentiment analysis based on parallel hybrid neural network model [J]. Journal of Computer Applications, 2019, 39(8): 2192-2197. |
[6] | WANG Liya, LIU Changhui, CAI Dunbo, LU Tao. Chinese text sentiment analysis based on CNN-BiGRU network with attention mechanism [J]. Journal of Computer Applications, 2019, 39(10): 2841-2846. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||