摘要
基于统计的主客观分析方法难以很好地反映中文的语义内涵,而基于语义的主客观分析方法需要大量的专家知识,且存在知识难以抽取,难以表示的问题。提出的基于语义的TriPos模式的中文主客观分析方法(SeTriPos)将基于统计的分析方法与基于语义的分析方法相结合,扩大了词的上下文定义范围,增加了简单、易于表示的语义规则,对分析结果进行调整,并通过实验的方法获得效果较好的实验参数。实验结果表明SeTriPos提高了主客观分析的判全率、判准率和F值,从而显示了该方法的合理性和有效性。
In the field of analyzing subjective and objective Chinese texts,the method based on statistic analysis can not fully describe the semantic meaning of Chinese and the method based on semantic analysis needs much expert knowledge and it is also difficulty of extracting and describing these semantic rules.To solve the above problem,this paper proposed an analysis method of subjective and objective Chinese texts based on semantic TriPos model（SeTriPos）.This method combined method based on statistic analysis and method based on semantic analysis.It enlarged the context of a word,used some relatively simple rules to adjust the analysis results and gains good values of the parameters through experiment results.The experiment results show that the algorithm is reasonable and effective
出处
《计算机应用研究》
CSCD
北大核心
2012年第9期3285-3288,共4页
Application Research of Computers
基金
安徽省教育厅重点资助项目(KJ2009A001Z)
安徽省科技厅重大科技专项资助项目(08010201002)
安徽大学青年科学研究基金资助项目(2009QN004A)
关键词
主客观分析
卡方统计
语义规则
analysis of subjective and objective text
chi-square statistic
semantic rule
