Show simple item record

dc.contributor.author曾华琳
dc.contributor.author周昌乐
dc.contributor.author陈毅东
dc.contributor.author史晓东
dc.date.accessioned2018-11-26T08:55:17Z
dc.date.available2018-11-26T08:55:17Z
dc.date.issued2016-04-11
dc.identifier.citation厦门大学学报(自然科学版),2016,55(03):108-114
dc.identifier.issn0438-0479
dc.identifier.otherXDZK201603018
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/165695
dc.description.abstract汉语隐喻计算是中文信息处理中的棘手难题之一.已有的隐喻识别研究多以人工方式分析和抽取隐喻特征,存在着主观性强、难以扩充的缺点,并且对于专业背景知识要求比较严格.本文基于大规模语料库的机器学习,利用最大熵分类模型,提出了一种最优特征模板自动抽取的隐喻识别算法,讨论了3种不同层次的特征模板,既包含了经典的简单特征,又将跨多个词的远距离上下文信息,以及描述语义信息的词语相似性引入特征模板进行考察.实验结果表明,该算法提高了隐喻识别准确率,是一种对于汉语隐喻计算行之有效的机器学习方法.
dc.description.abstractChinese metaphor computation is one of difficult problems in the Chinese information processing.It is very subjective and difficult for existing research methods by manually analyzing and extraction of metaphor feature.For the purpose of analyzing the traditional rule-based methods,a new machine learning method based on large scale corpus is proposed for metaphor recognition.The proposed method uses the maximum entropy model,and three different feature patterns,which are common features,large-scale context information,and the similarity of candidate words,to describe semantic information.Experimental results show that the proposed method can improve the accuracy of the metaphor recognition,and also indicate the effectiveness of the proposed machine learning method for metaphor computation.
dc.description.sponsorship国家自然科学基金(61573294);; 国家科技支撑计划(2012BAH14F03);; 教育部博士学科点基金博导类项目(20130121110040)
dc.language.isozh_CN
dc.subject汉语隐喻计算
dc.subject隐喻识别
dc.subject机器学习
dc.subject自动特征选择
dc.subjectChinses metaphor computation
dc.subjectmetaphor recognition
dc.subjectmachine learing
dc.subjectautomatic feature selection
dc.title基于特征自动选择方法的汉语隐喻计算
dc.title.alternativeChinese Metaphor Computation Based on Automatic Feature Selection
dc.typeArticle


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record