Unsupervised Relation Extraction by Mining Wikipedia Texts Using Information from the Web

Unsupervised Relation Extraction by Mining Wikipedia Texts Using Information from the Web
复制标题

DOI:
10.3115/1690219.1690289
复制
发表时间:
2009-08
期刊:
--
影响因子:
--
通讯作者:
Yulan Yan;Naoaki Okazaki;Y. Matsuo;Zhenglu Yang;M. Ishizuka
Yulan Yan;Naoaki Okazaki;Y. Matsuo;Zhenglu Yang;M. Ishizuka
中科院分区:
其他
文献类型:
--
作者:
Yulan Yan;Naoaki Okazaki;Y. Matsuo;Zhenglu Yang;M. Ishizuka

文献摘要

被引文献

相似文献

本文提出了一种无监督关系提取方法,用于发现和增强维基百科中特定概念参与的关系。利用维基百科文章和网络语料库的各自特征,我们开发了一种基于模式组合的聚类方法:来自维基百科文本依赖性分析的依赖性模式,以及由与网络相关的高度冗余信息生成的表面模式。对两个不同领域所提出的方法的评估证明了模式组合相对于现有方法的优越性。从根本上说,我们的方法展示了深层语言模式如何与网络表面模式互补地促进各种关系的生成。
This paper presents an unsupervised relation extraction method for discovering and enhancing relations in which a specified concept in Wikipedia participates. Using respective characteristics of Wikipedia articles and Web corpus, we develop a clustering approach based on combinations of patterns: dependency patterns from dependency analysis of texts in Wikipedia, and surface patterns generated from highly redundant information related to the Web. Evaluations of the proposed approach on two different domains demonstrate the superiority of the pattern combination over existing approaches. Fundamentally, our method demonstrates how deep linguistic patterns contribute complementarily with Web surface patterns to the generation of various relations.