面向中文专利sao结构抽取的文本特征比较研究-中文信息技术专业.pdfVIP

网络出版地址：/kcms/doi/10.13209/j.0479-8023.2015.049.html 北京大学学报(自然科学版) Acta Scientiarum Naturalium Universitatis Pekinensis doi: 10.13209/j.0479-8023.2015.049 面向中文专利SAO 结构抽取的文本特征比较研究 饶齐 王裴岩 张桂平† 沈阳航空航天大学知识工程研究中心 , 沈阳 110136; † 通信作者 , E-mail: zgp@ 摘要 针对中文专利文本中 SAO 结构实体关系抽取问题, 使用支持向量机的机器学习方法进行关系抽取实 验, 分别对基本词法信息、实体间距离信息、最短路径闭包树句法信息以及词向量信息等特征的有效性进行 验证分析。实验结果表明, 基本的词法信息能够明显提高关系抽取性能 , 而句法信息没有显著提高关系抽取 效果。此外, 也验证了词向量在 SAO 结构关系抽取中的可行性。 关键词 SAO 结构 ; 关系抽取 ; 特征有效性; 词向量 中图分类号 TP391 Text Feature Analysis on SAO Structure Extraction from Chinese Patent Literatures † RAO Qi, WANG Peiyan, ZHANG Guiping Knowledge Engineering Research Center, Shenyang Aerospace University, Shenyang 110136; † Corresponding author, E-mail: zgp@ Abstract To resolve the problem of SAO-based relation extraction from Chinese patent literatures, a series of experiments were implemented by using Support Vector Machines. It focused on the analysis of the validity of basic lexical information, syntactic information such as the shortest path enclosed trees, and distance features used in related works. The results show that simple lexical features can contribute to a good performance, while syntactic features cannot bring a remarkable improvement. Moreover, the feasibility of a new representation