计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230200086-7.doi: 10.11896/jsjkx.230200086

• 人工智能 • 上一篇    下一篇

面向海关进出口商品税率检测的归纳交互网络模型

吴安奇1, 车超1, 张强1,2, 周东生1   

  1. 1 大连大学先进设计与智能计算省部共建教育部重点实验室 大连 116622
    2 大连理工大学计算机科学与技术学院 大连 116086
  • 发布日期:2023-11-09
  • 通讯作者: 张强(liubin@dlut.edu.cn)
  • 作者简介:(wuanqiyes@163.com)
  • 基金资助:
    高等学校学科创新引智计划(D23006);辽宁省“兴辽英才计划”(XLYC2008017);国家自然科学基金(62076045,62102058);辽宁省教育厅服务地方项目(揭榜挂帅)(LJKFZ20220290)

Inductive Interactive Network Model for Customs Import and Export Commodity Tax Rate Detection

WU Anqi1, CHE Chao1, ZHANG Qiang1,2, ZHOU Dongsheng1   

  1. 1 Key Laboratory of Advanced Design and Intelligent Computing,Ministry of Education,Dalian University,Dalian 116622,China
    2 School of Computer Science and Technology,Dalian University of Technology,Dalian 116086,China
  • Published:2023-11-09
  • About author:WU Anqi,born in 1997,postgraduate.His main research interests include natural language processing and so on.
    ZHANG Qiang,born in 1971,Ph.D,professor.His main research interests include biological computing and artificial intelligence,big data analysis and processing.
  • Supported by:
    111 Project(D23006),LiaoNing Revitalization Talents Program(XLYC2008017),National Natural Science Foundation(62076045,62102058) and Educational Department of Liaoning Provincial(LJKFZ20220290).

PDF (PC)

469

摘要： 中国海关传统的人工商品税率审查方式存在效率低、判断依据不一致、精度不高等问题,使用文本分类方法对商品分类自动确定税率可以有效降低海关税率风险。但面向海关商品数据进行分类时,商品类别具有层次性,同一大类下的许多子类别的商品描述具有高度相似性,给商品分类带来了很大的挑战。因此,提出了一种归纳交互网络模型,在BERT和CNN基础上加入归纳和交互指导模块。在归纳模块中采用动态路由算法对CNN提取的特征进行迭代运算,可以有效解决相邻特征融合和冗余问题。同时,为了解决不同子类别之间特征相似问题,提高分类性能,引入交互指导模块,该模块主要是将归纳模块提取的特征信息同[CLS]分类向量进行交互。在真实的海关数据集上进行实验,实验结果表明,该方法能达到较好的效果,其中准确率高达92.98%,且性能明显优于各基线模型。

关键词: 中国海关, 税率检测, 归纳交互, 动态路由, 交互指导

Abstract: The traditional way of examining the tax rate of manual goods in China Customs has problems such as low efficiency,inconsistent judgment basis and low precision.Using text classification method to automatically determine the tax rate of commodity classification can effectively reduce the risk of customs tax rate.However,when classifying customs commodity data,commodity categories are hierarchical.Many sub-categories under the same category have highly similar commodity descriptions,which brings great challenges to commodity classification.Therefore,an inductive interactive network model is proposed,and inductive and interactive guidance modules are added on the basis of BERT and CNN.In the induction module,the dynamic routing algorithm is used to perform iterative operation on the features extracted by CNN,which can effectively solve the problem of adjacent feature fusion and redundancy.At the same time,in order to solve the feature similarity problem between different subcategories and improve the classification performance,the interactive guidance module is introduced,which is mainly to interact the feature information extracted by the induction module with [CLS] classification vector.Experiment is carried out on the real customs data set,and the results show that the method can achieve good results,the accuracy is up to 92.98%,and the performance is obviously better than that of each baseline model.

Key words: China Customs, Tax rate detection, Inductive interaction, Dynamic routing, Interactive guidance

中图分类号: 

  • TP391
[1]KIM Y.Convolutional Neural Networks for Sentence Classifica-tion[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing.2014:1746-1751.
[2]JOHNSON R,ZHANG T.Deep Pyramid Convolutional NeuralNetworks for Text Categorization[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:562-570.
[3]PETERS M E,NEUMANN M,IYYER M,et al.Deep contextualized word representations[C]//Annual Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2018:2227-2237.
[4]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isAll You Need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:6000-6010.
[5]DEVLIN J,CHANG M W,LEE K,et al.BERT:Pretraining of Deep Bidirectional Transformers for Language Understanding[C]//The North American Chapter of the Association for Computational Linguistics.2018:4171-4186.
[6]KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNetClassification with Deep Convolutional Neural Networks[C]//Conference and Workshop on Neural Information Processing Systems.2012:1097-1105.
[7]CONNEAU A,SCHWENK H,BARRAULT L,et al.Very deep convolutional networks for natural language processing [J].KI- Künstliche Intell,2016,26(6):180-189.
[8]SABOUR S,FROSST N,HINTON G E.Dynamic Routing Between Capsules[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:3856-3866.
[9]JOHNSON R,ZHANG T.Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding [J].Advances in neural information processing systems,2015,28(5):919-927.
[10]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.2017:562-570.
[11]NGUYEN H,NGUYEN M.A Deep Neural Architecture for Sentence-Level Sentiment Classification in Twitter Social Networking[C]//Computational Linguistics:15th International Conference of the Pacific Association for Computational Linguistics.PACLING,2018:15-27.
[12]ADAMS B,MCKENZIE G.Crowdsourcing the character of a place:Character-level convolutional networks for multilingual geographic text classification [J].Transactions in GIS,2018,22(2):394-408.
[13]YANG Z,YANG D,DYER C,et al.Hierarchical atten-tion networks for document classification[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2016:1480-1489.
[14]BAHDANAU D,CHO K H,BENGIO Y.Neural machine translation by jointly learning to align and translate[C]//3rd International Conference on Learning Representation.ICLR,2015.
[15]CHENG J,DONG L,LAPATA M.Long short-term memory-networks for machine reading [J].EMNLP,2016:551-561.
[16]SUN S,SUN Q,ZHOU K,et al.Hierarchical attention prototypical networks for few-shot text classification[C]//Proceedings of the 019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.2019:476-485.
[17]MUBAROK M S,ADIWIJAYA,ALDHI M D.Aspect-based sentiment analysis to review products using Naïve Bayes[C]//AIP conference proceedings.AIP Publishing LLC.2017:020060.
[18]MA Y,PENG H,CAMBRIA E.Targeted aspect-based senti-ment analysis via embedding commonsense knowledge into an attentive LSTM[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018:5876-5883.
[19]FAN F,FENG Y,ZHAO D.Multi-grained attention network for aspect-level sentiment classification[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:3433-3442.
[20]TAN M,DOS SANTOS C,XIANG B,et al.Improved representation learning for question answer matching[C]//Proceedings of the 54th Annual Meeting of the Association for Computa-tional Linguistics.2016:464-473.
[21]HOWARD J,RUDER S.Universal Language Model Fine-tuningfor Text Classification[C]//Proceedings of the 56th Annual Meeting of the As sociation for Computational Linguistics.2018:328-339.
[22]YU Y,SI X,HU C,et al.A review of recurrent neural networks:LSTM cells and network architectures [J].Neural Computation,2019,31(7):1235-1270.
[23]OQUAB M,BOTTOU L,LAPTEV I,et al.Learning and transferring mid-level image representations using convolutional neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:1717-1724.
[24]FLORIDI L,CHIRIATTI M.GPT-3:Its nature,scope,limits,and consequences [J].Minds and Machines,2020,30(4):681-694.
[25]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[26]LIU Y,OTT M,GOYAL N,et al.RoBERTa:A Robustly Optimized BERT Pretraining Approach [J].arXiv:1907.11692,2019.
[27]LEWIS M,LIU Y,GOYAL N,et al.BART:Denoising se-quence-to-sequence pretraining for natural language generation,translation,and comprehension[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:7871-7880.
[28]SUN Y,WANG S,FENG S,et al.ERNIE 3.0:Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation [J].arXiv:2107.02137,2021.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发