学术论文中问题与方法识别及其关系抽取研究综述

doi:10.13266/j.issn.0252-3116.2022.12.012

图书情报工作 ›› 2022, Vol. 66 ›› Issue (12): 125-138.DOI: 10.13266/j.issn.0252-3116.2022.12.012

学术论文中问题与方法识别及其关系抽取研究综述

张颖怡¹, 章成志¹, Daqing, He²

1. 南京理工大学经济管理学院信息管理系南京 210094;
2. 匹兹堡大学计算与信息学院匹兹堡 15260

收稿日期:2021-11-22 修回日期:2022-03-31 出版日期:2022-06-20 发布日期:2022-06-25
通讯作者: 章成志,教授,博士,博士生导师,通信作者,E-mail: zhangcz@njust.edu.cn
作者简介:张颖怡,博士研究生;Daqing He,教授,博士生导师。

A Review of Problem and Method Recognition and Relation Extraction in Academic Papers

Zhang Yingyi¹, Zhang Chengzhi¹, Daqing He

1. Department of Information Management, School of Economics and Management, Nanjing University of Science & Technology, Nanjing 210094;
2. School of Computing and Information, University of Pittsburgh, Pittsburgh 15260

Received:2021-11-22 Revised:2022-03-31 Online:2022-06-20 Published:2022-06-25

摘要/Abstract

摘要： [目的/意义]问题和方法是学术论文的重要组成部分。将散落在学术论文中的问题与方法进行有效组织,例如问题与方法识别及其之间的关系抽取,可挖掘学术论文中的隐性知识,促进学科的方法体系和问题体系构建。对学术论文中问题与方法识别及其关系抽取的相关研究工作的梳理,有助于把握该研究的发展趋势、发现该研究中存在的不足,并为未来的工作提供借鉴和指导。[方法/过程]在学术论文的问题和方法的挖掘方面,现有研究围绕4个研究点展开,分别是问题与方法及其关系定义、问题与方法及其关系标注数据集构建、问题与方法识别及其关系抽取的模型设计以及问题与方法及其关系的应用。本文分别对这4个研究点进行梳理,归纳总结现有学术论文中问题和方法知识挖掘的现状。[结果/结论]分析发现,在问题与方法的相关定义中,较少结合科学哲学中的问题学等理论进行定义;在问题与方法数据集构建中,存在数据集重复标注的现象,另外,开源数据集集中在自然科学领域且一般为英语语料,中文开源语料稀缺;在问题与方法识别及其关系抽取中,现有抽取模型性能较低;有关问题和方法的研究不应止步于词语识别和关系抽取,需对挖掘出的知识进行深入分析和应用。

关键词: 问题识别, 方法识别, 关系抽取, 学术论文信息挖掘

Abstract: [Purpose/Significance] Problems and methods are important parts of academic papers. Effectively organizing the problems and methods scattered in the academic papers, such as problem and method recognition and their relationship extraction, can mine the tacit knowledge in the academic papers and promote the construction of the method system and problem system in a discipline. To sort out previous studies on problem and method recognition and relationship extraction in academic papers, we can grasp the development trend, discover the shortcomings in this research, and provide guidance for future work. [Method/Process] In terms of mining problems and methods in academic papers, recent research was carried out around four research points, i.e., the definition of problems, methods and their relationship, the construction of problems, methods and their relationship datasets, problem and method recognition and relationship extraction methods, and the application of problems, methods and their relationship. This paper sorted out these four research points separately and summarized the current situation of knowledge mining of problems and methods in academic papers. [Result/Conclusion] The analysis finds that in the definitions of problems and methods, they seldom take the theories such as problemology in the philosophy of science into account; In problem and method dataset construction, there is a phenomenon of repeated annotations. Furthermore, most open-source datasets are in the field of natural science and are generally English corpus, while Chinese open-source corpus are scarce; In the problem and method recognition and relationship extraction, the performance of the existing extraction model is still low; The mining of problems and methods should not stop at concept recognition and relationship extraction, and in-depth analysis and application of the extracted knowledge is required.

Key words: problem recognition, method recognition, relationship extraction, information mining of academic papers

中图分类号:

G254

张颖怡, 章成志, Daqing, He. 学术论文中问题与方法识别及其关系抽取研究综述[J]. 图书情报工作, 2022, 66(12): 125-138.

Zhang Yingyi, Zhang Chengzhi, Daqing He. A Review of Problem and Method Recognition and Relation Extraction in Academic Papers[J]. Library and Information Service, 2022, 66(12): 125-138.

参考文献

[1] 杨信礼.社会发展动力机制的结构、功能与运行过程[J].中共中央党校学报, 2002, 6(4):28-33.
[2] 李丹.科学研究活动中的知识管理研究[D].武汉:武汉大学, 2005.
[3] 林定夷.问题与科学研究:问题学之探究[M].广州:中山大学出版社, 2006.
[4] BORNMANN L, MUTZ R. Growth rates of modern science:a bibliometric analysis based on the number of publications and cited references[J]. Journal of the Association for Information Science&Technology, 2015, 66(11):2215-2222.
[5] 科技部.关于破除科技评价中"唯论文"不良导向的若干措施(试行)[EB/OL].[2021-11-19]. https://www.cas.cn/zcjd/202002/t20200223_4735451.shtml.
[6] 中华人民共和国教育部.中共中央国务院印发《深化新时代教育评价改革总体方案》[EB/OL].[2021-11-19]. http://www.moe.gov.cn/jyb_xxgk/moe_1777/moe_1778/202010/t20201013_494381.html.
[7] 国务院办公厅.国务院办公厅关于完善科技成果评价机制的指导意见[EB/OL].[2021-08-02]. http://www.gov.cn/zhengce/content/2021-08/02/content_5628987.htm.
[8] 王海燕,潘云涛,马峥,等.基于科学研究问题成熟度的未来高影响力科技论文预测研究[J].情报学报, 2016, 35(1):36-47.
[9] 王玉琢,章成志.考虑全文本内容的算法学术影响力分析研究[J].图书情报工作, 2017, 61(23):6-14.
[10] 章成志,丁睿祎,王玉琢.基于学术论文全文内容的算法使用行为及其影响力研究[J].情报学报, 2018, 37(12):1175-1187.
[11] 钱佳佳,罗卓然,陆伟.基于问题-方法组合的科技论文新颖性度量与创新类型识别[J].图书情报工作, 2021, 65(14):82-89.
[12] 王艳艳,张均胜,乔晓东,等.基于问题-方法矩阵的文献新颖性评估方法[J].情报理论与实践, 2021, 44(2):90-95.
[13] NASAR Z, JAFFRY S W, MALIK M K. Information extraction from scientific articles:a survey[J]. Scientometrics, 2018, 117(3):1931-1990.
[14] ZHENG A, ZHAO H, LUO Z, et al. Improving on-line scientific resource profiling by exploiting resource citation information in the literature[J]. Information processing&management, 2021, 58(5):1-13.
[15] WESTERGAARD D, STRFELDT H-H, TØNSBERG C, et al. A comprehensive and quantitative comparison of text-mining in 15 million full-text articles versus their corresponding abstracts[J]. PLoS computational biology, 2018, 14(2):e1005962.
[16] LIN J. Is searching full text more effective than searching abstracts?[J]. BMC bioinformatics, 2009, 10(1):1-15.
[17] 杜秀杰,赵大良.学术论文语言表达范式分析[J].编辑学报, 2018, 30(3):260-263.
[18] 程齐凯.学术文本的词汇功能识别[D].武汉:武汉大学, 2015.
[19] KOVAEVIC'A, KONJOVIC'Z, MILOSAVLJEVIC'B, et al. Mining methodologies from NLP publications:a case study in automatic terminology recognition[J]. Computer speech&language, 2012, 26(2):105-126.
[20] AUGENSTEIN I, DAS M, RIEDEL S, et al. Semeval 2017 task 10:scienceie-extracting keyphrases and relations from scientific publications[C]//Proceedings of the 11th international workshop on semantic evaluation. Vancouver:Association for Computational Linguistics, 2017:546-555.
[21] LUAN Y, HE L, OSTENDORF M, et al. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction[C]//Proceedings of the 2018 conference on empirical methods in natural language processing. Brussels:Association for Computational Linguistics, 2018:3219-3232.
[22] 索传军,赖海媚.学术论文问题知识元的类型与描述规则[J].中国图书馆学报, 2021, 47(2):95-109.
[23] GUPTA S, MANNING C D. Analyzing the dynamics of research by extracting key aspects of scientific papers[C]//Proceedings of 5th international joint conference on natural language processing. Chiang Mai:Asian Federation of Natural Language Processing, 2011:1-9.
[24] SINGH M, DAN S, AGARWAL S, et al. AppTechMiner:Mining applications and techniques from scientific articles[C]//Proceedings of the 6th international workshop on mining scientific publications. New York:Association for Computing Machinery, 2017:1-8.
[25] 蒋婷.学科领域本体学习及学术资源语义标注研究[D].南京:南京大学, 2017.
[26] HOUNGBO H, MERCER R E. Method mention extraction from scientific research papers[C]//Proceedings of the coling. Mumbai:The COLING 2012 Organizing Committee, 2012:1211-1222.
[27] 章成志,张颖怡.基于学术论文全文的研究方法实体自动识别研究[J].情报学报, 2020, 39(6):589-600.
[28] 王曰芬.文献计量法与内容分析法的综合研究[D].南京:南京理工大学, 2007.
[29] QASEMIZADEH B, SCHUMANN A-K. The ACL RD-TEC 2.0:a language resource for evaluating term extraction and entity recognition methods[C]//Proceedings of the tenth international conference on language resources and evaluation. Portoro:European Language Resources Association, 2016:1862-1868.
[30] BRACK A, D'SOUZA J, HOPPE A, et al. Domain-independent extraction of scientific concepts from research articles[C]//Proceedings of the advances in information retrieval. Lisbon:Springer, 2020:251-266.
[31] SOLDATOVA L N, KING R D. An ontology of scientific experiments[J]. Journal of the Royal Society Interface, 2006, 3(11):795-803.
[32] DESS D, OSBORNE F, RECUPERO D R, et al. Ai-kg:an automatically generated knowledge graph of artificial intelligence[C]//Proceedings of the international semantic Web conference. Online:Springer, 2020:127-143.
[33] SHUM S B, MOTTA E, DOMINGUE J. ScholOnto:an ontology-based digital library server for research documents and discourse[J]. International journal on digital libraries, 2000, 3(3):237-248.
[34] CICCARESE P, WU E, KINOSHITA J, et al. The SWAN scientific discourse ontology[J]. Journal of biomedical informatics, 2008, 41(5):739-751.
[35] GÁBOR K, BUSCALDI D, SCHUMANN A-K, et al. Semeval-2018 task 7:Semantic relation extraction and classification in scientific papers[C]//Proceedings of the 12th international workshop on semantic evaluation. New Orleans:Association for Computational Linguistics, 2018:679-688.
[36] TATEISI Y, OHTA T, PYYSALO S, et al. Typed entity and relation annotation on computer science papers[C]//Proceedings of the tenth international conference on language resources and evaluation. Portoro:European Language Resources Association, 2016:3836-3843.
[37] JAIN S, ZUYLEN M V, HAJISHIRZI H, et al. SciREX:a challenge dataset for document-level information extraction[C]//Proceedings of the 58th annual meeting of the Association for Computational Linguistics. Online:Association for Computational Linguistics, 2020:7506-7516.
[38] MONDAL I, HOU Y, JOCHIM C. End-to-end construction of nlp knowledge graph[C]//Proceedings of the findings of the Association for Computational Linguistics. Online:Association for Computational Linguistics, 2021:1885-1895.
[39] 吴婷,孔芳.基于图注意力卷积神经网络的文档级关系抽取[J].中文信息学报, 2021, 35(10):73-80.
[40] NAN G, GUO Z, SEKULI I, et al. Reasoning with latent structure refinement for document-level relation extraction[C]//Proceedings of the 58th annual meeting of the Association for Computational Linguistics. Online:Association for Computational Linguistics, 2020:1546-1557.
[41] 黄萃,陈静,陈惠玲.第四研究范式:数据驱动下的人文社科研究模式跃迁[J].中国高校科技, 2021(10):10-14.
[42] 储荷婷.图书馆情报学界的研究方法:实践与发展[J].国家图书馆学刊, 2014, 23(3):3-14.
[43] CHU H, KE Q. Research methods:what's in the name?[J]. Library&information science research, 2017, 39(4):284-294.
[44] HOWISON J, BULLARD J. Software in the scientific literature:Problems with seeing, finding, and using software mentioned in the biology literature[J]. Journal of the Association for Information Science and Technology, 2015, 67(9):2137-2155.
[45] HEFFERNAN K, TEUFEL S. Identifying problems and solutions in scientific text[J]. Scientometrics, 2018, 116(2):1367-1382.
[46] QASEMIZADEH B. Investigating context parameters in technology term recognition[C]//Proceedings of the coling workshop on synchronic and diachronic approaches to analyzing technical language. Dublin:Dublin City University and Association for Computational Linguistics, 2014:1-10.
[47] 程齐凯,李信.面向语义出版的学术文本词汇语义功能自动识别[J].数字图书馆论坛, 2017(8):24-31.
[48] TUAROB S, BHATIA S, MITRA P, et al. AlgorithmSeer:a system for extracting and searching for algorithms in scholarly big data[J]. IEEE transactions on big data, 2016, 2(1):3-17.
[49] 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. Minneapolis:Association for Computational Linguistics, 2019:4171-4186.
[50] BELTAGY I, LO K, COHAN A. SciBERT:a pretrained language model for scientific text[C]//Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing. Hong Kong:Association for Computational Linguistics, 2019:3615-3620.
[51] FÄRBER M, ALBERS A, SCHVBER F. Identifying used methods and datasets in scientific publications[C]//Proceedings of the SDU@AAAI. Online:AAAI, 2021:1-9.
[52] JIANG M, D'SOUZA J, AUER S, et al. Improving scholarly knowledge representation:evaluating bert-based models for scientific relation classification[C]//Proceedings of the international conference on Asian digital libraries. Online:Springer, 2020:3-19.
[53] LUAN Y, OSTENDORF M, Hajishirzi H. Scientific information extraction with semi-supervised neural tagging[C]//Proceedings of the 2017 conference on empirical methods in natural language processing. Copenhagen:Association for Computational Linguistics, 2017:2641-2651.
[54] WADDEN D, WENNBERG U, LUAN Y, et al. Entity, relation, and event extraction with contextualized span representations[C]//Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing. Hong Kong:Association for Computational Linguistics,2019:5784-5789.
[55] ZHONG Z, CHEN D. A frustratingly easy approach for joint entity and relation extraction[C]//Proceedings of the NAACL-HLT. Online:Association for Computational Linguistics, 2021:50-61.
[56] PETERS M, NEUMANNR 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. New Orleans:Association for Computational Linguistics, 2018:2227-2237.
[57] KAMEDA A, UCHIYAMA K, Takeda H, et al. Extraction of semantic relationships from academic papers using syntactic patterns[C]//Proceedings of eKNOW. Nice:IARIA, 2013:32-35.
[58] MIWA M, SASAKI Y. Modeling joint entity and relation extraction with table representation[C]//Proceedings of the 2014 conference on empirical methods in natural language processing. Doha:Association for Computational Linguistics, 2014:1858-1869.
[59] BARIK B, MARSI E. NTNU-2 at SemEval-2017 task 10:Identifying synonym and hyponym relations among keyphrases in scientific documents[C]//Proceedings of the 11th international workshop on semantic evaluation. Vancouver:Association for Computational Linguistics, 2017:965-968.
[60] LEE J Y, DERNONCOURT F, SZOLOVITS P. MIT at SemEval-2017 Task 10:Relation extraction with convolutional neural networks[C]//Proceedings of the 11th international workshop on semantic evaluation. Vancouver:Association for Computational Linguistics, 2017:978-984.
[61] DAI Q, INOUE N, REISERT P, et al. Improving scientific relation classification with task specific supersense[C]//Proceedings of the 32nd Pacific Asia conference on language, information and computation. Hong Kong:Association for Computational Linguistics, 2018:129-138.
[62] PAN X, YAN E, CUI M, et al. How important is software to library and information science research?a content analysis of full-text publications[J]. Journal of informetrics, 2019, 13(1):397-406.
[63] 聂辉华,江艇,杨汝岱.中国工业企业数据库的使用现状和潜在问题[J].世界经济,2012,35(5):142-158.

学术论文中问题与方法识别及其关系抽取研究综述

A Review of Problem and Method Recognition and Relation Extraction in Academic Papers

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

[1]	卓可秋, 沈思, 王东波. 自有知识增强下的学术全文本关系抽取研究[J]. 图书情报工作, 2022, 66(7): 120-131.
[2]	董美, 常志军. 一种面向中医领域科技文献的实体关系抽取方法[J]. 图书情报工作, 2022, 66(18): 105-113.
[3]	余传明, 王曼怡, 安璐. 跨语言情境下基于对抗的实体关系抽取模型研究[J]. 图书情报工作, 2020, 64(17): 131-144.
[4]	赵华茗, 钱力, 余丽. 依存句法特征的科研命名实体识别算法[J]. 图书情报工作, 2020, 64(11): 108-115.
[5]	蒋婷, 孙建军. 学术资源本体非等级关系抽取研究[J]. 图书情报工作, 2016, 60(20): 112-122.
[6]	谷俊. 中文专利本体半自动构建系统设计[J]. 图书情报工作, 2013, 57(03): 105-111,146.