Please wait a minute...
Advanced Search
现代图书情报技术  2015, Vol. 31 Issue (10): 81-87    DOI: 10.11925/infotech.1003-3513.2015.10.11
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
自动标注中文专利的引文信息
姜春涛
南京大学计算机科学与技术系 南京 210023;
江苏省专利信息服务中心 南京 210008
Automatic Annotation of Bibliographical References in Chinese Patent Documents
Jiang Chuntao
Department of Computer Science and Technology, Nanjing University, Nanjing 210023, China;
Patent Information and Service Center of Jiangsu Province, Nanjing 210008, China
全文: PDF(431 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

[目的] 自动标注嵌入中文专利文本中的专利、标准、学术论文、其他专著4类引用信息。[方法] 对于专利、标准和其他专著的引用, 应用模式匹配的方法标注; 对于学术论文的引用, 应用由两阶段构成的机器学习方法标注, 自动检测含有引用的句子, 并从中自动提取6类文献特征信息。[结果] 10层交叉验证的结果表明: 专利引用标注的精确度和查全度均为100%, 标准引用标注的精确度和查全度分别达到92%和94%, 而其他专著引用标注的精确度和查全度分别达到80%和71%; 标注学术论文引用的精确度和查全度在阶段一分别为95.7%和96.0%, 阶段二分别为95.3%和94.9%。[局限] 模式匹配方法需要人工分析大量的专利文件, 训练数据规模相对较小。[结论] 运用模式匹配方法标注专利、标准引用的性能高于92%; 运用机器学习方法标注学术论文引用的平均性能达到95%。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
Abstract

[Objective] This paper aims to automatically annotate four types of bibliographical references in Chinese patent documents, such as patents, standards, papers, and other monographs public documents. [Methods] Use a pattern matching approach to annotate the references of patents, standards, and public documents, and use a two-phase machine learning approach to annotate the paper references, firstly, automatically detecte the sentences that contain citation information, then extracte 6 categories of bibliographic features from the results. [Results] The results of ten-fold cross validation show that the accuracy for annotating patents is 100%, and the precision and recall for annotating standards is 92% and 94% respectively, while the precision and recall for annotating public documents is 80% and 71% respectively. For annotating paper references, the precision and recall in phase one is 95.7% and 96.0% and in phase two is 95.3% and 94.9% respectively. [Limitations] The pattern matching approach requires analyzing a lot of patent documents manually, and the size of the training model used by the proposed machine learning approach is relatively small. [Conclusions] The performance of annotating patents and standards using a pattern matching approach achieves over 92%, and the performance of annotating papers using a machine learning approach achieves 95%.

收稿日期: 2015-04-14     
:  TP393  
通讯作者: 姜春涛, ORCID: 0000-0001-8332-7858, E-mail: spring_surge@126.com。     E-mail: spring_surge@126.com
引用本文:   
姜春涛. 自动标注中文专利的引文信息[J]. 现代图书情报技术, 2015, 31(10): 81-87.
Jiang Chuntao. Automatic Annotation of Bibliographical References in Chinese Patent Documents. New Technology of Library and Information Service, DOI:10.11925/infotech.1003-3513.2015.10.11.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.1003-3513.2015.10.11

[1] Lopez P. Automatic Extraction and Resolution of Bibliographical References in Patent Documents [A].//Advances in Multidisciplinary Retrieval [M]. Springer Berlin Heidelberg, 2010: 120-135.
[2] Lai K K, Wu S J. Using the Patent Co-citation Approach to Establish a New Patent Classification System [J]. Information Processing and Management, 2005, 41(2): 313-330.
[3] Mayer M. Does Science Push Technology? Patents Citing Scientific Literature [J]. Research Policy, 2000, 29(3): 409-434.
[4] Adams S. The Text, the Full Text and Nothing but the Text: Part 1-Standards for Creating Textual Information in Patent Documents and General Search Implications [J]. World Patent Information, 2010, 32(1): 22-29.
[5] Lawson M, Kemp N, Lynch M F, et al. Automatic Extraction of Citations from the Text of English-language Patents - An Example of Template Mining [J]. Journal of Information Science, 1996, 22(6): 423-436.
[6] Agatonovic M, Aswani N, Bontcheva K, et al. Large-scale Parallel Automatic Patent Annotation [C]. In: Proceedings of the 1st ACM Workshop on Patent Information Retrieval. ACM, 2008.
[7] Lopez P, Romary L. Multiple Retrieval Models and Regression Models for Prior Art Search [C]. In:Proceedings of the 2009 Cross-Language Evaluation Forum Workshop. Springer, 2009.
[8] Peng F, McCallum A. Accurate Information Extraction from Research Papers Using Conditional Random Fields [C]. In: Proceedings of the 2002 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL). 2004: 329-336.
[9] Nanba H, Anzen N, Okumura M. Automatic Extraction of Citation Information in Japanese Patent Applications [J]. International Journal on Digital Library, 2008, 9(2): 151-161.
[10] Feng G, Chen X, Peng Z. A Rules and Statistical Learning Based Method for Chinese Patent Information Extraction [C]. In: Proceedings of the 8th Web Information Systems and Applications Conference. IEEE, 2011:114-118.
[11] 姜彩红, 乔晓东, 朱礼军. 基于本体的专利摘要知识抽取[J]. 现代图书情报技术, 2009(2): 23-28. (Jiang Caihong, Qiao Xiaodong, Zhu Lijun. Ontology-based Patent Abstracts' Knowledge Extraction [J]. New Technology of Library and Information Service, 2009(2): 23-28.)
[12] 王曰芬, 徐丹丹, 李飞. 专利信息内容挖掘及其试验研究[J]. 现代图书情报技术, 2008(12): 59-65. (Wang Yuefen, Xu Dandan, Li Fei. Experimental Study of Patent Information Content Mining [J]. New Technology of Library and Information Service, 2008(12): 59-65.)
[13] 于霜. 基于专利引文网络的空间关系可视化研究[D]. 大连: 大连理工大学, 2010. (Yu Shuang. Analysis on Visualization Among Spatial Relationship Based on Patent Citation Network [D]. Dalian: Dalian University of Technology, 2010.)
[14] 薄怀霞. 基于构建专利引文数据库的专利文献分析研究[D]. 曲阜: 曲阜师范大学, 2014. (Bo Huaixia. Patent Literature Analysis Study Based on Building Patent Citation Databases [D]. Qufu: Qufu Normal University, 2014.)
[15] Lafferty J D, Mccallum A, Pereira F C N. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data [C]. In: Proceedings of the 18th International Conference on Machine Learning. 2001: 282-289.
[16] Vapnik V N. The Nature of Statistical Learning Theory [M]. The 2nd Edition. Springer, 1999.
[17] Cho H C, Okazak N, Miwa M, et al. Named Entity Recognition with Multiple Segment Representations [J]. Information Processing and Management, 2013, 49(4): 954-965.
[18] Hall M, Frank E, Holmes G, et al. The WEKA Data Mining Software: An Update [J]. SIGKDD Explorations, 2009, 11(1): 10-18.
[19] Fan R E, Chang K W, Hsieh C J, et al. LibLinear: A Library for Large Linear Classification [J]. Journal of Machine Learning Research, 2008, 9(12): 1871-1874.
[20] Okazaki N. CRFsuite: A Fast Implementation of Conditional Random Fields [CP/OL]. [2015-03-24]. http://www.chokkan. org/software/crfsuite/.
[21] Nocedal J. Updating Quasi-Newton Matrices with Limited Storage [J]. Mathematics of Computation, 1980, 35(151): 773-782.
[22] Crammer K, Dekel O, Keshet J, et al. Online Passive Aggressive Algorithms [J]. Journal of Machine Learning Research, 2006, 7(3): 551-585.

[1] 曾庆田,胡晓慧,李超. 融合主题词嵌入和网络结构分析的主题关键词提取方法 *[J]. 数据分析与知识发现, 2019, 3(7): 52-60.
[2] 夏立新,曾杰妍,毕崇武,叶光辉. 基于LDA主题模型的用户兴趣层级演化研究 *[J]. 数据分析与知识发现, 2019, 3(7): 1-13.
[3] 杨宁, 黄飞虎, 文奕, 陈云伟. 基于微博用户行为的观点传播模型[J]. 现代图书情报技术, 2015, 31(12): 34-41.
[4] 余昕聪, 李红莲, 吕学强. 本体上下位关系在招生问答机器人中的应用研究[J]. 现代图书情报技术, 2015, 31(12): 65-71.
[5] 王政军, 俞小怡, 金玉玲. 利用旁路监听技术约束数字资源过量下载[J]. 现代图书情报技术, 2015, 31(12): 95-100.
[6] 刘占兵, 肖诗斌. 基于用户兴趣模糊聚类的协同过滤算法[J]. 现代图书情报技术, 2015, 31(11): 12-17.
[7] 伍万坤, 吴清烈, 顾锦江. 基于EM-LDA综合模型的电商微博热点话题发现[J]. 现代图书情报技术, 2015, 31(11): 33-40.
[8] 强韶华, 吴鹏. 地域性差异视角下的网站分类用户心智模型空间性研究[J]. 现代图书情报技术, 2015, 31(11): 68-74.
[9] 秦学东. 基于Drupal的KVM私有云管理系统解决方案[J]. 现代图书情报技术, 2015, 31(11): 91-95.
[10] 吴江, 张劲帆. 社会网络三元结构中关注影响力研究——以学生关系网络为例[J]. 现代图书情报技术, 2015, 31(10): 72-80.
[11] 王颖, 张智雄, 李传席, 刘毅, 汤怡洁, 周子健, 钱力, 付鸿鹄. 科技知识组织体系开放引擎系统的设计与实现[J]. 现代图书情报技术, 2015, 31(10): 95-101.
[12] 桂思思, 陆伟, 黄诗豪, 周鹏程. 融合主题模型及多时间节点函数的用户兴趣预测研究[J]. 现代图书情报技术, 2015, 31(9): 9-16.
[13] 秦晓慧, 乐小虬. 面向单篇文献引文网络的主题来源与走向追踪[J]. 现代图书情报技术, 2015, 31(9): 52-59.
[14] 邓启平, 王小梅. 利用LeaderRank识别有影响力的作者[J]. 现代图书情报技术, 2015, 31(9): 60-67.
[15] 郑海山. 图书馆数据中心基础架构部署自动化系统[J]. 现代图书情报技术, 2015, 31(9): 97-101.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn