Please wait a minute...
Data Analysis and Knowledge Discovery  2022, Vol. 6 Issue (11): 79-92    DOI: 10.11925/infotech.2096-3467.2022.0185
Current Issue | Archive | Adv Search |
Knowledge Modeling and Association Q&A for Policy Texts
Hua Bin1,2,Kang Yue1(),Fan Linhao2
1School of Management Science and Engineering, Tianjin University of Finance and Economics, Tianjin 300222, China
2School of Science and Technology, Tianjin University of Finance and Economics, Tianjin 300222, China
Download: PDF (2455 KB)   HTML ( 11
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper develops a smart question-answering model for association policy based on cognitive semantic knowledge understanding, aiming to improve the government services. [Methods] First, we established a model based on policy connotation to express policy knowledge. Then, we introduced the attention mechanism for question words and classified policy issues combining the improved ERNIE + CNN model. Third, we used the semantic role labeling IDCNN + CRF model and cognitive computing method to obtain the semantics and pragmatic knowledge. Finally, based on knowledge fusion and semantic retrieval, we utilized knowledge aggregation technology to generate relevant answers. We also adopted the BERT semantic similarity calculation and knowledge unit measurement to evaluate the quality of answers. [Results] The accuracy of problem classification reached 90.76%, which was 18.81% and 5.05% higher than those of the original BERT and ERNIE models. The precision of problem knowledge acquisition reached 95.88%, and the accuracy of the answer quality reached 93.75%. The semantic similarity of the answers was 0.88, while the knowledge consistency was 0.96. [Limitations] The performance of our model is limited by the integrity of the domain knowledge system, while the answers’ relevance relies on the accuracy of policy knowledge extraction. [Conclusions] Based on the deconstruction of policy contents and scientific knowledge representation, the proposed method can generate answers for questions on different policy contents.

Key wordsIntelligent Question and Answering      Text Mining      E-Government      Policy Knowledge Model      Knowledge Graph      Knowledge Aggregation     
Received: 07 March 2022      Published: 13 January 2023
ZTFLH:  TP391  
Corresponding Authors: Kang Yue     E-mail: 18502612743@163.com

Cite this article:

Hua Bin,Kang Yue,Fan Linhao. Knowledge Modeling and Association Q&A for Policy Texts. Data Analysis and Knowledge Discovery, 2022, 6(11): 79-92.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2022.0185     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2022/V6/I11/79

The Framework of Policy Association Question Answering
The Construction of the Policy Knowledge Model
The Structure of QAM-ERNIE-CNN
关系名称 语义关系描述
has_content (具有政策内容) 政策与政策内容之间的关系
has_subject(具有政策主体) 政策与政策主体之间的关系
has_object(具有政策客体) 政策内容与政策客体之间的关系
has_event(具有事件) 政策内容与事件之间的关系
has_action(具有动作) 政策内容与动作之间的关系
has_central(具有国家级) 政策主体与中央政府之间的关系
has_local(具有地方级) 政策主体与地方政府之间的关系
has_park(具有园区级) 政策主体与产业园区之间的关系
Description of the Semantic Relationship Between Concepts
The Result of Optimal Threshold Knowledge Fusion
The Knowledge Graph of One Policy
问题类别 训练集数量 验证集数量 测试集数量
事实类 8 466 2 117 184
列表类 2 135 534 296
判断类 64 16 160
方法类 776 194 246
计数类 4 061 1 015 39
原因类 52 13 18
选择类 33 8 9
总数 15 587 3 897 952
The Statistics of Problems Classification Data
模型 Model(no QAM) Model(QAM)
准确率/% 损失 准确率/% 损失
BERT 71.95 1.10 77.94 0.85
BERT-CNN 76.16 0.98 80.36 0.90
BERT-RNN 68.80 1.40 69.85 1.30
BERT-RCNN 68.07 1.20 71.64 1.10
BERT-DPCNN 69.01 1.10 70.38 1.00
ERNIE 85.71 0.61 87.08 0.51
ERNIE-CNN 87.36 0.49 90.76 0.46
The Result of the Classification
The Analysis of Efficiency in Question Processing
问题类别 q s i m均值 k r均值 k r '均值 k d i f均值 q c o n均值
事实类(29) 0.958 1.770 1.753 0.034 0.991
方法类(25) 0.920 1.657 1.467 0.600 1.020
原因类(13) 0.768 2.769 2.231 0.846 0.859
The Result of Answer Quality Evaluation Average
The Example of a Double Layer Policy Search Query
The Knowledge Retrieval of Related Supporting Policies
The Analysis of Efficiency in Knowledge Retrieving
政府部门 天津市人才奖补政策内容汇总
天津市科技局 《关于构建天津市市场导向的绿色技术创新体系的落实方案》第二章第3条规定:健全绿色创新人才激励机制…
《市科技局关于抢抓机遇加强引进外国高端人才的工作措施》第7条规定:提供专项支持…
天津市滨海高新区管委会 《天津滨海高新区促进信息技术应用创新产业发展办法》第5条规定:年收入达30万元的人才…
《天津滨海高新技术产业开发区促进新经济服务业高质量发展办法(暂行)》第7条规定:高端人才奖励…
天津市工信局 《天津市支持中小企业高质量发展的若干政策》第9条规定:支持利用企业资源开展培训…
配套政策 天津市人才奖补相关配套政策内容汇总
保险政策 天津市医疗保障局《天津市基本医疗保险付费总额管理办法(试行)》…
天津市人社局《天津市登记失业人员就业创业扶持政策清单》…
天津滨海高新区管委会《滨海新区就业扶持补贴资金管理暂行办法》…
子女政策 天津市人社局《天津市就业困难人员认定办法》…
天津市人民政府办公厅《天津市推动非户籍人口在城市落户工作方案》…
天津市科技局《天津市关于强化实施创新驱动发展战略进一步推进大众创业万众创新深入发展的实施意见》…
The Example of Policy Associated Answer Generation (Part)
[1] 工业和信息化部. 工业和信息化部中小企业局关于印发《中小企业数字化赋能服务产品及活动推荐目录(第一期)》的通知[EB/OL].(2020-04-21). https://www.miit.gov.cn/jgsj/qyj/wjfb/art/2020/art_4d845224c9ee4d4aa061841fb3f6014b.html.
[1] (Ministry of Industry and Information Technology. Notice of the Small and Medium-Sized Enterprise Bureau of the Ministry of Industry and Information Technology on the Issuance of the Recommended Catalogue of Digital Empowerment Service Products and Activities for Small and Medium-Sized Enterprises(Phase I)[EB/OL].(2020-04-21). https://www.miit.gov.cn/jgsj/qyj/wjfb/art/2020/art_4d845224c9ee4d4aa061841fb3f6014b.html.)
[2] 国务院办公厅. 国务院办公厅关于印发2021年政务公开工作要点的通知[EB/OL].(2021-04-23). http://www.gov.cn/zhengce/content/2021-04/23/content_5601602.htm.
[2] (General Office of the State Council. Notice of the General Office of the State Council on the Issuance of Key Points of Government Affairs Publicity in 2021[EB/OL].(2021-04-23). http://www.gov.cn/zhengce/content/2021-04/23/content_5601602.htm.)
[3] Graesser A C, Murachver T. Symbolic Procedures of Question Answering[A]//The Psychology of Questions[M]. London: Routledge, 2017: 15-88.
[4] Carter M. Minds and Computers: An Introduction to the Philosophy of Artificial Intelligence[M]. Edinburgh,UK: Edinburgh University Press, 2007.
[5] Turing A M. Computing Machinery and Intelligence[A]//Parsing the Turing Test[M]. Dordrecht: Springer Netherlands, 2007: 23-65.
[6] 叶浩生. 身心二元论的困境与具身认知研究的兴起[J]. 心理科学, 2011, 34(4):999-1005.
[6] (Ye Haosheng. The Dilemma of Dualism and the Rising of Embodied Cognition Programme[J]. Journal of Psychological Science, 2011, 34(4): 999-1005.)
[7] Kiefer F. Morphology and Pragmatics[A]//The Handbook of Morphology[M]. Oxford, UK: Blackwell Publishing Ltd., 2017: 272-279.
[8] Bhati R, Prasad S S. Open Domain Question Answering System Using Cognitive Computing[C]// Proceedings of 2016 6th International Conference-Cloud System and Big Data Engineering(Confluence). 2016: 34-39.
[9] 于晶. 基于社会化问答社区涌现模式分析的领域热点识别研究[J]. 情报学报, 2021, 40(2): 213-222.
[9] (Yu Jing. Detection of Hotspot in Scientific Fields Based on Emerging Pattern Analysis of Social Q&A Community Contents[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(2): 213-222.)
[10] Indurkhya N, Damerau F J. Handbook of Natural Language Processing[M]. Chapman and Hall/CRC, 2010.
[11] Roberts K, Alam T, Bedrick S, et al. TREC-COVID: Rationale and Structure of an Information Retrieval Shared Task for COVID-19[J]. Journal of the American Medical Informatics Association, 2020, 27(9): 1431-1436.
doi: 10.1093/jamia/ocaa091 pmid: 32365190
[12] 温有奎, 温浩, 乔晓东. 让知识产生智慧——基于人工智能的文本挖掘与问答技术研究[J]. 情报学报, 2019, 38(7): 722-730.
[12] (Wen Youkui, Wen Hao, Qiao Xiaodong. Research on the Methods of Information Science and Artificial Intelligence Fusion Innovation[J]. Journal of the China Society for Scientific and Technical Information, 2019, 38(7): 722-730.)
[13] Soares M A C, Parreiras F S. A Literature Review on Question Answering Techniques, Paradigms, and Systems[J]. Journal of King Saud University-Computer and Information Sciences, 2020, 32(6): 635-646.
doi: 10.1016/j.jksuci.2018.08.005
[14] Abacha A B, Zweigenbaum P. MEANS: A Medical Question-Answering System Combining NLP Techniques and Semantic Web Technologies[J]. Information Processing & Management, 2015, 51(5): 570-594.
doi: 10.1016/j.ipm.2015.04.006
[15] Abdi A, Idris N, Ahmad Z. QAPD: An Ontology-Based Question Answering System in the Physics Domain[J]. Soft Computing, 2018, 22(1): 213-230.
doi: 10.1007/s00500-016-2328-2
[16] Agarwal A, Sachdeva N, Yadav R K, et al. EDUQA: Educational Domain Question Answering System Using Conceptual Network Mapping[C]// Proceedings of 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing. 2019: 8137-8141.
[17] Kourtin I, Mbarki S, Mouloudi A. A Legal Question Answering Ontology-Based System[C]// Proceedings of International Conference on Automatic Processing of Natural-Language Electronic Texts with NooJ. 2020: 218-229.
[18] 陈璟浩, 曾桢, 李纲. 基于知识图谱的“一带一路”投资问答系统构建[J]. 图书情报工作, 2020, 64(12): 95-105.
doi: 10.13266/j.issn.0252-3116.2020.12.011
[18] (Chen Jinghao, Zeng Zhen, Li Gang. A Question Answering System for “the Belt and Road” Investment Based on Knowledge Graph[J]. Library and Information Service, 2020, 64(12): 95-105.)
doi: 10.13266/j.issn.0252-3116.2020.12.011
[19] 谭云丹. 科技政策智能问答系统架构及关键算法研究[D]. 重庆: 重庆邮电大学, 2020.
[19] (Tan Yundan. Research on Architecture and Key Algorithm of Question Answering for Science and Technology Policies[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2020.)
[20] 霍朝光, 钱毅, 祁天娇. 基于开放公文的新冠肺炎政策知识图谱构建与分析[J]. 档案学通讯, 2021(2): 53-62.
[20] (Huo Chaoguang, Qian Yi, Qi Tianjiao. The Construction and Analysis of Epidemic Prevention Policy Knowledge Graph Based on Open Administrative Documents[J]. Archives Science Bulletin, 2021(2): 53-62.)
[21] 刘勘, 徐勤亚, 於陆. 面向营商环境的知识图谱构建研究[J]. 数据分析与知识发现, 2022, 6(4): 82-96.
[21] (Liu Kan, Xu Qinya, Yu Lu. Constructing Knowledge Graph for Business Environment[J]. Data Analysis and Knowledge Discovery, 2022, 6(4): 82-96.)
[22] 武楷彪, 郎宇翔, 董瑜. 融合句法结构和词义信息的政策文本关联挖掘方法研究[J]. 数据分析与知识发现, 2022, 6(5): 20-33.
[22] (Wu Kaibiao, Lang Yuxiang, Dong Yu. Mining Policy Text Relevance with Syntactic Structure and Semantic Information[J]. Data Analysis and Knowledge Discovery, 2022, 6(5): 20-33.)
[23] Kryftis Y, Grammatikou M, Kalogeras D, et al. Policy-Based Management for Federation of Virtualized Infrastructures[J]. Journal of Network and Systems Management, 2017, 25(2): 229-252.
doi: 10.1007/s10922-016-9390-z
[24] 李晗佶, 陈海庆. 机器翻译技术困境的哲学反思[J]. 大连理工大学学报(社会科学版), 2020, 41(6): 122-128.
[24] (Li Hanji, Chen Haiqing. Philosophical Reflection on the Technical Dilemma of Machine Translation[J]. Journal of Dalian University of Technology(Social Sciences), 2020, 41(6): 122-128.)
[25] Kreutzer R T, Sirrenberg M. Understanding Artificial Intelligence[M]. Cham: Springer International Publishing, 2020.
[26] 李超, 柴玉梅, 南晓斐, 等. 基于深度学习的问题分类方法研究[J]. 计算机科学, 2016, 43(12): 115-119.
doi: 10.11896/j.issn.1002-137X.2016.12.020
[26] (Li Chao, Chai Yumei, Nan Xiaofei, et al. Research on Problem Classification Method Based on Deep Learning[J]. Computer Science, 2016, 43(12): 115-119.)
doi: 10.11896/j.issn.1002-137X.2016.12.020
[27] Tomasello M. Cognitive Linguistics[A]//A Companion to Cognitive Science[M]. Oxford, UK: Blackwell Publishing Ltd., 2017: 477-487.
[28] 李金鹏, 张闯, 陈小军, 等. 自动文本摘要研究综述[J]. 计算机研究与发展, 2021, 58(1): 1-21.
[28] (Li Jinpeng, Zhang Chuang, Chen Xiaojun, et al. Survey on Automatic Text Summarization[J]. Journal of Computer Research and Development, 2021, 58(1): 1-21.)
[29] Ganesan K. ROUGE 2.0: Updated and Improved Measures for Evaluation of Summarization Tasks[OL]. arXiv Preprint, arXiv:1803.01937.
[30] 华斌, 吴诺, 贺欣. 基于知识融合的政务信息化项目多专家审批意见整合[J]. 数据分析与知识发现, 2021, 5(10): 124-136.
[30] (Hua Bin, Wu Nuo, He Xin. Integrating Expert Reviews for Government Information Projects with Knowledge Fusion[J]. Data Analysis and Knowledge Discovery, 2021, 5(10): 124-136.)
[31] 王春城. 政策精准性与精准性政策——“精准时代”的一个重要公共政策走向[J]. 中国行政管理, 2018(1): 51-57.
[31] (Wang Chuncheng. To Achieve Precision of Policy and Policy with Precision: A Significant Orientation of Public Policy in Precisiondepended Times[J]. Chinese Public Administration, 2018(1): 51-57.)
[32] Sun Y, Wang S H, Li Y K, et al. ERNIE 2.0: A Continual Pre-training Framework for Language Understanding[OL]. arXiv Preprint, arXiv: 1907.12412.
[33] 马相东, 张文魁, 刘丁一. 地方政府招商引资政策的变迁历程与取向观察:1978—2021年[J]. 改革, 2021(8): 131-144.
[33] (Ma Xiangdong, Zhang Wenkui, Liu Dingyi. The Changing Course and Orientation of Local Government’s Investment Promotion and Capital Introduction Policies: 1978—2021[J]. Reform, 2021(8): 131-144.)
[34] 国家质量监督检验检疫总局, 中国国家标准化管理委员会. 党政机关电子公文格式规范第1部分:公文结构: GB/T 33476.1—2016[S]. 北京: 中国标准出版社, 2016.
[34] (General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China, Standardization Administration of the People’s Republic of China. Format Specification for Electronic Official Document of Party and Government Organs—Part 1: Official Document Structure: GB/T 33476.1—2016[S]. Beijing: Standards Press of China, 2016.)
[1] Liu Chunjiang, Li Shuying, Hu Hanlin, Fang Shu. Graph Databases for Complex Network Analysis[J]. 数据分析与知识发现, 2022, 6(7): 1-11.
[2] Zhang Han, An Xinyu, Liu Chunhe. Building Multi-Source Semantic Knowledge Graph for Drug Repositioning[J]. 数据分析与知识发现, 2022, 6(7): 87-98.
[3] Liu Kan, Xu Qinya, Yu Lu. Constructing Knowledge Graph for Business Environment[J]. 数据分析与知识发现, 2022, 6(4): 82-96.
[4] Zhang Wei, Wang Hao, Chen Yuetong, Fan Tao, Deng Sanhong. Identifying Metaphors and Association of Chinese Idioms with Transfer Learning and Text Augmentation[J]. 数据分析与知识发现, 2022, 6(2/3): 167-183.
[5] Liu Zhenghao, Qian Yuxing, Yi Tianlong, Lv Huakui. Constructing Knowledge Graph for Financial Securities and Discovering Related Stocks with Knowledge Association[J]. 数据分析与知识发现, 2022, 6(2/3): 184-201.
[6] Cheng Zijia, Chen Chong. Question Comprehension and Answer Organization for Scientific Education of Epidemics[J]. 数据分析与知识发现, 2022, 6(2/3): 202-211.
[7] Hou Dang, Fu Xiangling, Gao Songfeng, Peng Lei, Wang Youjun, Song Meiqi. Mining Enterprise Associations with Knowledge Graph[J]. 数据分析与知识发现, 2022, 6(2/3): 212-221.
[8] Shang Rongxuan, Zhang Bin, Mi Jianing. End-to-End Aspect-Level Sentiment Analysis for E-Government Applications Based on BRNN[J]. 数据分析与知识发现, 2022, 6(2/3): 364-375.
[9] Deng Lu,Hu Po,Li Xuanhong. Abstracting Biomedical Documents with Knowledge Enhancement[J]. 数据分析与知识发现, 2022, 6(11): 1-12.
[10] Zhou Yang,Li Xuejun,Wang Donglei,Chen Fang,Peng Lijuan. Visualizing Knowledge Graph for Explosive Formula Design[J]. 数据分析与知识发现, 2021, 5(9): 42-53.
[11] Shen Kejie, Huang Huanting, Hua Bolin. Constructing Knowledge Graph with Public Resumes[J]. 数据分析与知识发现, 2021, 5(7): 81-90.
[12] Ruan Xiaoyun,Liao Jianbin,Li Xiang,Yang Yang,Li Daifeng. Interpretable Recommendation of Reinforcement Learning Based on Talent Knowledge Graph Reasoning[J]. 数据分析与知识发现, 2021, 5(6): 36-50.
[13] Huang Mingxuan,Jiang Caoqing,Lu Shoudong. Expanding Queries Based on Word Embedding and Expansion Terms[J]. 数据分析与知识发现, 2021, 5(6): 115-125.
[14] Li He,Liu Jiayu,Li Shiyu,Wu Di,Jin Shuaiqi. Optimizing Automatic Question Answering System Based on Disease Knowledge Graph[J]. 数据分析与知识发现, 2021, 5(5): 115-126.
[15] Xu Guang,Ren Ming,Song Chengyu. Extracting China’s Economic Image from Western News[J]. 数据分析与知识发现, 2021, 5(5): 30-40.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn