Chinese Patent Efficacy Phrase Recognition
Effect information,as foundation of the patent efficacy analysis,the completeness and accuracy has the decisive significance to analysis result.In order to improve the efficiency of extraction of effect information,the paper proposed one kind method based on conditional random field model (CRFs) to recognize effect phrases.Efficacy phrases are highly generalization,and divided into effect theme,attribute and the efficiency value of three parts.Phrase recognition is recognition of the three parts.We make use of the sentence features in which the phrases exit,the lexical features and clue words with the composite template to discriminate the efficacy phrase on Patent abstract file.The experimental results show that the proposed method is effective,accurate rate is 79.25%,the recall rate is 56.7%.
effect information conditional random field phrase recognition composite template
Ting Hou Xueqiang Lv Liping Xu
Beijing Key Laboratory of Internet Culture and Digital Dissemination Research,Beijing Information Sc Beijing Research Center of Urban System Engineering, Beijing, China
国际会议
重庆
英文
510-514
2015-03-02（万方平台首次上网日期，不代表论文的发表时间）