[1]贾真,何大可,杨燕,等.基于弱监督学习的中文网络百科关系抽取[J].智能系统学报,2015,10(1):113-119.[doi:10.10.3969/j.issn.1673-4785.201311017]
JIA Zhen,HE Dake,YANG Yan,et al.Relation extraction from Chinese online encyclopedia based on weakly supervised learnin[J].CAAI Transactions on Intelligent Systems,2015,10(1):113-119.[doi:10.10.3969/j.issn.1673-4785.201311017]
点击复制
JIA Zhen,HE Dake,YANG Yan,et al.Relation extraction from Chinese online encyclopedia based on weakly supervised learnin[J].CAAI Transactions on Intelligent Systems,2015,10(1):113-119.[doi:10.10.3969/j.issn.1673-4785.201311017]
基于弱监督学习的中文网络百科关系抽取
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
10
期数:
2015年第1期
页码:
113-119
栏目:
学术论文—机器学习
出版日期:
2015-03-25
- Title:
- Relation extraction from Chinese online encyclopedia based on weakly supervised learnin
- Keywords:
- knowledge acquisition; information extraction; relation extraction; weakly supervised learning; bootstrapping; Chinese online encyclopedia; conditional random fields; naive Bayes
- 分类号:
- TP391
- 文献标志码:
- A
- 摘要:
- 实体关系抽取在信息检索、自动问答、本体学习等领域都具有重要作用。提出了基于弱监督学习的关系抽取框架。首先利用知识库中已有结构化的关系三元组,从自然语言文本中自动获取训练语料;针对训练语料数量较少导致特征不足的问题,采用基于朴素贝叶斯的句子分类器和基于自扩展的训练方法,从未标注数据中获取更多的训练语料;然后利用条件随机场模型训练关系抽取器。实验结果表明所提方法的有效性,有现有方法相比,文中方法获得较高的准确率。
- Abstract:
- Entity relation extraction plays an important role in the fields of information retrieval, automatic question answering and ontology learning. An entity relation extraction frame based on weakly-supervised learning is proposed in the paper. First, training data are acquired automatically from natural language texts by using relation triples in structured knowledge base. To solve the problem that the number of training data is small and features are insufficient, a bootstrapping method is used to train sentence classifiers based on naive Bayes model. This method can acquire more training data from unlabelled data. The relation extractors are trained by using conditional random fields (CRF) model. The experiment results showed that the method is feasible and effective. Compared with the existing methods state-of-the-art method, the proposed method achieves high accuracy.
- 参考文献/References:
-
[1] RIEDEL S, YAO L, MCCALLUM A. Modeling relations and their mentions without labeled text[J]. Machine Learning and Knowledge Discovery in Databases, 2010, 6323: 148-163.
[2] ZHANG T, Regularized winnow methods[J]. Advance in Neural Information Processing Systems, 2001(13):703-709.
[3] KAMBHATLA N. Combining lexical, syntactic and semantic features with maximum entropy models for extracting relations[C]//Proceedings of the ACL, 2004 on Interactive Poster and Demonstration Sessions. Barcelona, Spain, 2004: 178-181.
[4] TRATZ S, HOVY E. ISI: automatic classification of relations between nominals using a maximum entropy classifier[C]//Proceedings of the 5th International Workshop on Semantic Evaluation. Uppsala, Sweden, 2010: 222-225.
[5] ZELENKO D, AONE C, RICHARDELLA A. Kernel methods for relation extraction [J]. Machine Learning, 2003(3):1083-1106.
[6] GIULIANO C, LAVELLI A, PIGHIN D, et al. FBK-IRST: Kernel methods for semantic relation extraction[C]//Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007). Prague, Czech, 2007: 141-144.
[7] 程显毅, 朱倩. 未定义类型的关系抽取的半监督学习框架研究[J]. 南京大学学报:自然科学版, 2012, 48(4): 466-474.CHENG Xianyi, ZHU Qian. A study of relation extraction of undefined relation type based on semi-supervised learning framework[J]. Journal of Nanjing University: Natural Sciences, 2012, 48(4): 466-474.
[8] BOLLEGALA D, MATSUO Y, ISHIZUKA M. Relational duality: unsupervised extraction of semantic relations between entities on the Web[C]//Proceedings of the 19th World Wide Web Conference. New York, 2010: 151-160.
[9] YAN Y, OKACAKI N, MATSUO Y, et al. Unsupervised relation extraction by mining Wikipedia texts using information from the Web[C]//Proceedings of the Joint Conference of the 46th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Singapore, 2009: 1021-1029.
[10] CRAVEN M, KUMLIEN J. Constructing biological knowledge bases by extracting information from text sources[C]//Proceedings of the 7th International Conference on Intelligent Systems for Molecular Biology. Palo Alto, CA, 1999: 77-86.
[11] WU F, DANIEL S W. Autonomously semantifying wikipedia[C]//Proceedings of the ACM Sixteenth Conference on Information and Knowledge Management. New York, 2007: 41-50.
[12] BUNESCU R C, MOONEY R J. Learning to extract relations from the web using minimal supervision[C]//Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, 2007: 567-570.
[13] MINTZ M, BILLS S, SNOW R. Distant supervision for relation extraction without labeled data[C]//Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, 2009: 1003-1011.
[14] YAO LM, RIEDEL S, MCAALLUM A. Collective cross document relation extraction without labeled data[C]//Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, 2010: 1013-1023.
[15] SURDANU M, MCCLOSKY D, TIBSHIRANI J, et al. A simple distant supervision approach for the TAC-KBP slot filling task [C]//Proceedings of the Text Analysis Conference 2010-Knowledge Base Population Worksho.[s.l.], 2010:1-5.
[16] 陈立玮, 冯岩松, 赵东岩. 基于弱监督学习的海量网络数据关系抽取[J]. 计算机研究与发展, 2013, 50(9): 1825-1835.CHEN Liwei, FENG Yansong, ZHAO Dongyan. Extracting relations from the web via weakly supervised learning[J]. Journal of Computer Research and Development, 2013, 50(9): 1825-1835.
[17] 尹红风, 贾真, 李天瑞, 等. 西南交通大学中文分词[EB/OL]. [2012-07-24]. http://ics.swjtu.edu.cn.YIN Hongfeng, JIA Zhen, LI Tianrui, et al. Southwest Jiaotong University Chinese Segmentation [EB/OL]. [2012-07-24]. http://ics.swjtu.edu.cn.
[18] CHE W X, LI Z H, LIU T. LTP: a Chinese language technology platform[C]//Proceedings of the Coling 2010.[s.l.], 2010: 13-16.
[19] 田久乐, 赵蔚. 基于同义词词林的词语相似度计算方法[J]. 吉林大学学报: 自然科学版, 2010, 28(6): 602-608.TIAN Jiule, ZHAO Wei. Words similarity algorithm based on Tongyici Cilin in semantic Web adaptive learning system[J]. Journal of Jilin University: Inform ation Science Edition, 2010, 28(6): 602-608.
[20] 张雪英, 闾国年. 基于字面相似度的地理信息分类体系自动转换方法[J].遥感学报, 2008, 12(3): 433-440.ZHANG Xueying, LU Guonian. Approach to automatic conversion of geographic information classification schemes[J]. Journal of Remote Sensing, 2008, 12(3): 433-440.
[21] LAFFERTY J, PEREIRA F, MCCALUM A. Conditional random fields: probabilistic models for segmenting and labeling sequence data[C]//Proceedings of 18th International Conference on Machine Learning. San Francisco: AAAI Press, 2001: 282-289.
[22] 张佳宝. 基于条件随机场的中文命名实体识别研究[D]. 长沙:国防科技大学, 2010:45-59.ZHANG Jiabao. The research on conditional random fields based Chinese named entity recognition[D]. Changsha: National University of Defense Technology, 2010: 45-59.
- 相似文献/References:
-
[1]王定桥,李卫华,杨春燕.从用户需求语句建立问题可拓模型的研究[J].智能系统学报,2015,10(6):865.[doi:10.11992/tis.201507038]
WANG Dingqiao,LI Weihua,YANG Chunyan.Research on building an extension model from user requirements[J].CAAI Transactions on Intelligent Systems,2015,10():865.[doi:10.11992/tis.201507038]
[2]胡小康,王俊红.基于相容模糊概念的规则提取方法[J].智能系统学报,2016,11(3):352.[doi:10.11992/tis.201603043]
HU Xiaokang,WANG Junhong.Research on rule extraction method based on compatibility fuzzy concept[J].CAAI Transactions on Intelligent Systems,2016,11():352.[doi:10.11992/tis.201603043]
[3]汤建国,汪江桦,韩莉英,等.基于覆盖粗糙集的语言动力系统[J].智能系统学报,2014,9(2):229.[doi:10.3969/j.issn.1673-4785.201307018]
TANG Jianguo,WANG Jianghua,HAN Liying,et al.Linguistic dynamic systems based on covering-based rough sets[J].CAAI Transactions on Intelligent Systems,2014,9():229.[doi:10.3969/j.issn.1673-4785.201307018]
[4]于润羽,杜军平,薛哲,等.面向科技学术会议的命名实体识别研究[J].智能系统学报,2022,17(1):50.[doi:10.11992/tis.202107010]
YU Runyu,DU Junping,XUE Zhe,et al.Research on named entity recognition for scientific and technological conferences[J].CAAI Transactions on Intelligent Systems,2022,17():50.[doi:10.11992/tis.202107010]
[5]黄河燕,刘啸.面向新领域的事件抽取研究综述[J].智能系统学报,2022,17(1):201.[doi:10.11992/tis.202109045]
HUANG Heyan,LIU Xiao.A survey on event extraction in new domains[J].CAAI Transactions on Intelligent Systems,2022,17():201.[doi:10.11992/tis.202109045]
备注/Memo
收稿日期:2013-11-7;改回日期:。
基金项目:国家自然科学基金资助项目(61170111,61134002,61202043,61262058).
作者简介:贾真,1975年生,女,讲师,主要研究方向为内容安全、信息抽取、知识工程。四川省计算机学会大数据专委会委员,中国计算机学会中文信息技术专委会委员;何大可,1944年生,男,教授,博士生导师,中国密码学会副理事长、学术委员会委员,信息安全国家重点实验室第四届学术委员会委员,全国并行计算专业委员会委员,中国电子学会高级会员。主要研究方向为信息安全、内容安全、并行计算。曾获陕西省及国家教委科技进步二等奖、国家自然科学四等奖。发表学术论文240余篇,出版专著3部;杨燕,1964年生,女,教授,博士生导师,博士,主要研究方向为数据挖掘、计算智能、集成学习。ACM成都分部副主席,中国计算机学会人工智能与模式识别专委会委员和理论计算机科学专委会委员,中国人工智能学会机器学习专委会委员和粗糙集与软计算专委会委员。曾获四川省优秀教学成果二等奖,校优秀教学成果一、二等奖,发表学术论文120余篇,出版专著1部。
通讯作者:贾真.E-mail:zjia@home.swjtu.edu.cn.
更新日期/Last Update:
2015-06-16