不确定性环境下的矛盾知识主张识别研究

doi:10.13266/j.issn.0252-3116.2021.20.013

图书情报工作 ›› 2021, Vol. 65 ›› Issue (20): 123-134.DOI: 10.13266/j.issn.0252-3116.2021.20.013

不确定性环境下的矛盾知识主张识别研究

郭进京, 黄奇

南京大学信息管理学院, 南京 210023

收稿日期:2021-05-17 修回日期:2021-08-09 出版日期:2021-10-20 发布日期:2021-10-22
通讯作者: 黄奇(ORCID:0000-0003-2394-148X),教授,博士,博士生导师,通讯作者,E-mail:huangq@nju.edu.cn
作者简介:郭进京(ORCID:0000-0003-1590-8014),博士研究生。

Research on Identification of Contradictory Knowledge Claims Under the Uncertainty Environment

Guo Jinjing, Huang Qi

School of Information Management, Nanjing University, Nanjing 210023

Received:2021-05-17 Revised:2021-08-09 Online:2021-10-20 Published:2021-10-22

摘要/Abstract

摘要： [目的/意义] 科学研究（尤其是医学研究）充满了不确定性，识别研究中的矛盾知识主张将有助于识别"科学分歧/不一致的科学结论"，推动潜在变革性科学研究的识别和相关研究的完善。[方法/过程] 以阿尔茨海默病为例，将PubMed文摘数据作为数据源，采用SemRep工具进行三元组抽取。制定表征矛盾意义的知识主张识别规则，依据不确定性程度高低对来源语句进行划分，分别采用单句识别和跨语句识别两种途径，识别以三元组形式表示的、具有矛盾意义的医学研究知识主张。[结果/结论] 从来源于PubMed的6 574篇医学文摘中共计识别出49组（涉及277对三元组）矛盾知识主张。阿尔茨海默病在诊断和治疗方面的研究仍存在部分争议和矛盾，有待进一步验证。矛盾知识主张识别为潜在变革性医学研究前沿发现提供新思路，可用于基于知识计量的知识发现和为知识图谱可信度计算提供参考。

关键词: 知识发现, 不确定性, 矛盾知识, SPO, 阿尔茨海默病

Abstract: [Purpose/significance] Scientific research, especially medical research, is full of uncertainty. Identifying contradictory knowledge claims in research will help identify "scientific divergence/inconsistent scientific conclusions", promote identification of potentially transformative scientific research and improve related research. [Method/process] Taking Alzheimer's disease as an example, this article used SemRep to extract triples from the PubMed abstract data. Based on the knowledge claim identification rules that represented contradictory meanings, this article classified source sentences according to the degree of uncertainty and used single-sentence recognition and cross-sentence recognition respectively to identify contradictory medical research knowledge claims expressed in the form of triples. [Result/conclusion] A total of 49 groups (involving 277 pairs of triples) contradictory knowledge claims are identified from 6574 PubMed medical abstracts. There are still some controversies and contradictions in the diagnosis and treatment of Alzheimer's disease, which need to be further verified. The identification of contradictory knowledge claims provides new ideas for the frontier discoveries of potentially transformative medical research, which can be used for knowledge discovery based on knowledge measurement and provide references for the reliability calculation of knowledge graph.

Key words: knowledge discovery, uncertainty, contradictory knowledge, SPO, Alzheimer's disease

中图分类号:

G250

郭进京, 黄奇. 不确定性环境下的矛盾知识主张识别研究[J]. 图书情报工作, 2021, 65(20): 123-134.

Guo Jinjing, Huang Qi. Research on Identification of Contradictory Knowledge Claims Under the Uncertainty Environment[J]. Library and Information Service, 2021, 65(20): 123-134.

参考文献

[1] JAMES M. Law reform[J]. London Review, 1835, 2(3):1-51.
[2] 吴国林.论知识的客观性[J]. 科学学与科学技术管理, 2000, 21(6):37-39.
[3] LIGHT M, QIU X Y, SRINIVASAN P. The language of bioscience:facts, speculations, and statements in between[C]//HLT-NAACL 2004 workshop:linking biological literature, ontologies and databases. Boston:Association for Computational Linguistics, 2004:17-24.
[4] The Cell editorial team. What happens next[J]. Cell, 2021, 184(2):291-292.
[5] Alzheimer's Disease International. Dementia facts & figures[EB/OL].[2021-02-24]. https://www.alzint.org/about/dementia-facts-figures/.
[6] 中国老年医学会. 倡议书:我国应持续加大对阿尔茨海默病的重视与投入[EB/OL].[2021-02-24]. https://www.zglnyxxh.com/site/content/3036.html.
[7] KUHN T S, HACKING I. The structure of scientific revolutions:50th anniversary edition[M]. Chicago:University of Chicago Press, 2012:72-89.
[8] 杜建. 医学知识不确定性测度的进展与展望[J]. 数据分析与知识发现, 2020, 4(10):14-27.
[9] Oxford-Dictionary. Oxford english dictionary online, 2nd edition[EB/OL].[2021-02-24]. http://www.oed.com/.
[10] CHEN C M, SONG M. Representing scientific knowledge:the role of uncertainty[M]. Switzerland:Springer International Publishing, 2017:1-351.
[11] MCELROY M W. The new knowledge management:complexity, learning, and sustainable innovation[M] Burlington:Elsevier Butterworth-Heinemann, 2003:7.
[12] PETERS K, MARUSTER L, JORNA R J. Knowledge claim evaluation:a fundamental issue for knowledge management[J]. Journal of knowledge management, 2010, 14(2):243-257.
[13] ALAMRI A. The detection of contradictory claims in biomedical abstracts[D]. Sheffield:University of Sheffield, 2016.
[14] MARNEFFE M, RAFFERTY A N, MANNING C D. Finding contradictions in text[C]//Association for Computational Linguistics 2008:Proceedings of the 46th annual meeting of the association for computational linguistics.Stroudsburg:Association for Computational Linguistics, 2008:1039-1047.
[15] DAGAN I, GLICKMAN O, MAGNINI B. The PASCAL recognising textual entailment challenge[C]//Machine learning challenges. evaluating predictive uncertainty, visual object classification, and recognising tectual entailment. Southampton:Springer, 2005:177-190.
[16] HARABAGIU S M, HICKL A, LACATUSU V F. Negation, contrast and contradiction in text processing[C]//AAAI'06:Proceedings of the 21st national conference on artificial intelligence. Menlo Park:The AAAI Press, 2006:755-762.
[17] KILICOGLU H, PENG Z, TAFRESHI S, et al. Confirm or refute?:a comparative study on citation sentiment classification in clinical research publications[J]. Journal of biomedical informatics, 2019, 91(3):103123.
[18] MURRAY D, LAMERS W, BOYACK K, et al. Measuring disagreement in science[C]//Proceedings of the 17th international conference of the international society for scientometrics and informetrics(ISSI). Leuven:ISSI Society, 2019:2370-2375.
[19] ROSEMBLAT G, FISZMAN M, SHIN D, et al. Towards a characterization of apparent contradictions in the biomedical literature using context analysis[J]. Journal of biomedical informatics, 2019, 98(10):103275.
[20] PINTO J M G, WAWRZINEK J, BALKE W. What drives research efforts? find scientific claims that count![C]//Proceedings of the 2019 ACM/IEEE joint conference on digital libraries. Washington:IEEE Press, 2019:217-226.
[21] LI X Y, PENG S Y, DU J. Towards medical knowmetrics:representing and computing medical knowledge using semantic predications as the knowledge unit and the uncertainty as the knowledge context[J].Scientometrics,2021,126(7):6225-6251.
[22] Turing Center. Open information extraction[EB/OL].[2021-02-24].https://openie.allenai.org/.
[23] IHS Markit. Patent solutions for research and discovery[EB/OL].[2021-02-24]. https://ihsmarkit.com/products/patents-applications.html.
[24] RINDFLESCH T C, FISZMAN M. The interaction of domain knowledge and linguistic structure in natural language processing:interpreting hypernymic propositions in biomedical text[J]. Journal of Biomedical Informatics, 2003, 36(6):462-477.
[25] RINDFLESCH T C, LIBBUS B, HRISTOVSKI D, et al. Semantic relations asserting the etiology of genetic diseases[C]//AMIA Annual symposium proceedings/AMIA Symposium. Rockville:American Medical Informatics Association, 2003:554-558.
[26] FISZMAN M, DEMNER-FUSHMAN D, LANG F M, et al. Interpreting comparative constructions in biomedical text[C]//Biological, translational, and clinical language processing. Prague:Association for Computational Linguistics, 2007:137-144.
[27] KILICOGLU H, ROSEMBLAT G, FISZMAN M, et al. Broad-coverage biomedical relation extraction with SemRep[J]. BMC Bioinformatics, 2020, 21(1):1-28.
[28] KHAN M A, YUAN Y, IQBAL U, et al. No association linking short-term proton pump inhibitor use to dementia:systematic review and meta-analysis of observational studies[J]. American journal of gastroenterology, 2020, 115(5):671-678.
[29] MADHAV D, VENKAT N, SACHIN S, et al. Proton pump inhibitors do not increase the risk of dementia:a systematic review and meta-analysis of prospective studies[J]. Diseases of the esophagus, 2020,33(10):1-9.
[30] HAYNES R B. Of studies, syntheses, synopses, summaries, and systems:the "5S" evolution of information services for evidence-based healthcare decisions[J]. Evidence based medicine, 2006, 11(6):162-164.
[31] SMALL H. What makes some scientific findings more certain than others? a study of citing sentences for low-hedged papers[C]//Proceedings of the 17th international conference on scientometrics and informetrics(ISSI). Leuven:ISSI Society, 2019:554-560.
[32] LUCCHETTA R C, MATA B P M D, MASTROIANNI P D C. Association between development of dementia and use of benzodiazepines:a systematic review and meta-analysis[J]. Pharmacotherapy:the journal of human pharmacology and drug therapy, 2018, 38(10):1010-1020.
[33] SU C, UNDERWOOD W, RYBALCHENKO N, et al. ERK1/2 and ERK5 have distinct roles in the regulation of brain-derived neurotrophic factor expression[J]. Journal of neuroscience research, 2011, 89(10):1542-1550.
[34] XIE B, ZHOU H M, LIU W X, et al. Evaluation of the diagnostic value of peripheral BDNF levels for Alzheimer's disease and mild cognitive impairment:results of a meta-analysis[J]. International journal of neuroscience, 2019, 130(1):1-14.
[35] 国家卫生健康委办公厅. 阿尔茨海默病的诊疗规范(2020年版)[J].全科医学临床与教育, 2021, 19(1):4-6.
[36] 卢超,章成志,王玉琢,等.语义特征分析的深化——学术文献的全文计量分析研究综述[J]. 中国图书馆学报, 2021, 47(2):110-131.
[37] SINYAVSKAYA L, GAUTHIER S, RENOUX C, et al. Comparative effect of statins on the risk of incident Alzheimer disease[J]. Neurology:official journal of the American academy of neurology, 2018, 90(3):179-187.
[38] 中共中央国务院印发《国家创新驱动发展战略纲要》[EB/OL].[2021-02-24]. http://www.gov.cn/xinwen/2016-05/19/content_5074812.htm.

不确定性环境下的矛盾知识主张识别研究

Research on Identification of Contradictory Knowledge Claims Under the Uncertainty Environment

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	陈晓红, 高凡, 朱维凤, 何雪梅, 杨勇, 夏琬钧, 张祖涛. 信息素养SPOC混合教学模式的设计与实现[J]. 图书情报工作, 2022, 66(9): 74-81.
[2]	邓君, 王阮. 口述历史档案资源知识图谱与多维知识发现研究[J]. 图书情报工作, 2022, 66(7): 4-16.
[3]	王延飞. 情报理论探索中的几个基本问题[J]. 图书情报工作, 2022, 66(20): 45-49.
[4]	丁培. 学术图表知识发现技术框架及研究进展[J]. 图书情报工作, 2021, 65(23): 136-148.
[5]	索传军, 李木子. 我国学术论文研究问题探析——基于2015-2020年图情领域CSSCI发表论文的实证研究[J]. 图书情报工作, 2021, 65(19): 105-116.
[6]	宋士杰, 齐云飞, 赵宇翔, 朱庆华. 冲突性健康信息对用户健康信息搜寻的影响:基于不确定性视角的探究[J]. 图书情报工作, 2021, 65(11): 24-32.
[7]	张永娟, 刘炜, 于建荣, 陈涛. 基于IIIF和语义知识图谱的印章资源整合与知识发现研究[J]. 图书情报工作, 2020, 64(7): 127-135.
[8]	李慧芳, 孟祥保. 近十年国内外图书馆资源发现系统研究与实践进展述评[J]. 图书情报工作, 2020, 64(6): 120-129.
[9]	李月琳, 张建伟, 包虹虹. 突发公共卫生事件情境下大学生的信息需求及满足程度[J]. 图书情报工作, 2020, 64(22): 85-95.
[10]	马鲁伟, 陈晓亮, 郑海山, 肖铮, 黄国凡, 萧德洪. 在线教学平台应急管理及图书馆应对策略——以厦门大学SPOC平台为例[J]. 图书情报工作, 2020, 64(15): 144-150.
[11]	徐源, 胡正银, 宋亦兵, 吴璇. 面向学科知识服务的微信小程序研究与实践[J]. 图书情报工作, 2020, 64(14): 54-62.
[12]	王雪, 武俊伟, 陈观群, 李燕琼, 马路. 阿尔茨海默病基因-疾病关联的知识挖掘[J]. 图书情报工作, 2020, 64(13): 120-132.
[13]	庞弘燊. 基于科技文献多重共现的数据模型理论与知识发现应用范例研究[J]. 图书情报工作, 2019, 63(9): 61-72.
[14]	付芸, 汪雪锋, 李佳, 侯雨佳. 基于SAO结构的创新解决方案遴选研究——以空气净化技术为例[J]. 图书情报工作, 2019, 63(6): 75-84.
[15]	李洁, 毕强, 许鹏程, 牟冬梅. 数字图书馆知识发现的数据驱动机制及绩效优化研究[J]. 图书情报工作, 2019, 63(3): 6-13.