基于规则的复句关系词的自动标识.pdfVIP

第 29 卷第1 期 中文信息学报 Vo l. 29 , No. 1 2015 年 1 月 JOURNAL OF CHINESE INFORMATION PROCESSING Jan. , 2015 文章编号: 1003-0077(2015)01-0044-05 基于规则的复旬关系词的自动标识 贾遂民1 ，雷利利2 ，胡明生l (1.郑州师范学院信息科学与技术学院，河南郑州 450044; 2. 河南财经税务高等专科学校综合实验实训中心，河南郑州 451464) 摘 要:关系词的自动标识是中文信息处理领域的基础性研究课题，该文利用规则实现其自动标识。首先通过语 料的分析总结出关系词在使用过程中的 12 种特征，以这些特征建立规则的约束条件;然后提出包含匹配算法实现 复句准关系词序列与规则索引坷的匹配，以此获取目标规则，并根据目标规则约束条件与关系词所在语境的匹配 结果得到匹配规则;最后利用匹配规则的结论实现关系词的自动标识。实验结果表明，该方法对关系询标识的正 确率达到 70.9% 。 关键词:关系词;规则;复句;自动标识 中图分类号: TP391 文献标i只码 :A Rule Based Identification of Compound Sentences Relation Words JIA Suimin1 , LEI Lili2 , HU Mingsheng1 (1. College of Information Science . Technology , Zhengzhou Normal University , Zhengzhou , Henan 450044 , China; 2. Comprehensive Experimental . Training Center , HeNan College of Finace . Taxation , Zhengzhou , Henan 451464 , China) Abstract: Automatic identifying the relation words of compound sentences is a fundamental issue in the field of Chi- nese information processing. This paper describe a rule based method for automatic identification of compound sen tence relation words. To construct the rule , 12 featuresare summarized from the corpus. Then a match algorithm is described to obtaind the candidate relation word sequence. Finally the context of the relation words is employed to match with the rules. Experiment results show that this method achieves an accuracy of 70. 9 %. Key words: relation words; rule; compound sentences; auto-identifying 加了关系词识别的难度。基于规则的研究是自然语 1 引言