All Title Author
Keywords Abstract


结合实体链接与实体聚类的命名实体消歧

DOI: 10.13190/j.jbupt.2014.05.008, PP. 36-40

Keywords: 命名实体消歧,实体链接,聚类

Full-Text   Cite this paper   Add to My Lib

Abstract:

为了消除文本中命名实体的歧义,提出了一种结合实体链接与实体聚类的命名实体消歧算法,结合2种方法,可弥补单独使用其中一种方法的局限.该算法在背景文本中将待消歧实体指称扩充为全称,使用扩充后的全称在英文维基百科知识库中生成候选实体集合,同时提取多种特征对候选实体集合进行排序,对于知识库中没有对应实体的指称使用聚类消歧.实验结果表明,该算法在KBP2011评测数据上的F值为0.746,在KBP2012评测数据上的F值为0.670.

References

[1]  赵军, 刘康, 周光有, 等. 开放式文本信息抽取[J]. 中文信息学报, 2011, 25(6): 98-110. Zhao Jun, Liu Kang, Zhou Guangyou, et al. Open text information extraction[J]. Journal of Chinese Information, 2011, 25(6): 98-110.
[2]  Bunescu R C, Pasca M. Using encyclopedic knowledge for named entity disambiguation[C]//Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics, 2006, 6: 9-16.
[3]  Cucerzan S. Large-scale named entity disambiguation based on wikipedia data[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 2007, 7: 708-716.
[4]  Monahan S, Lehmann J, Nyberg T, et al. Cross-lingual cross-document coreference with entity linking[C]//Proceedings of the Text Analysis Conference, 2011.
[5]  Tan Yongmei, Wang Zhichao, Yang Xue, et al. BUPTTeam participation at TAC 2012 knowledge base population[C]//Proceedings of the Text Analysis Conference, 2012.
[6]  Hachey B, Radford W, Nothman J, et al. Evaluating entity linking with wikipedia[J]. Artificial intelligence, 2013, 194: 130-150.
[7]  史天艺, 李明禄. 基于维基百科的自动词义消歧方法[J]. 计算机工程, 2009, 35(18): 62-66. Shi Tianyi, Li Minglu. Automatic word sense disambiguation method based on wikipedia[J\]. Computer Engineering, 2009, 35(18): 62-66.
[8]  杜婧君, 陆蓓, 谌志群. 基于中文维基百科的命名实体消歧方法[J]. 杭州电子科技大学学报, 2013, 32(6): 57-60. Du Jingjun, Lu Bei, Chen zhiqun. Named entity disambiguation[J]. Journal of Hangzhou Dianzi University, 2013, 32(6): 57-60.

Full-Text

comments powered by Disqus