点击次数：

论文类型： 期刊论文

发表时间： 2022-06-29

发表刊物： 大连理工大学学报

所属单位： 电子信息与电气工程学部

卷号： 52

期号： 5

页面范围： 761-766

ISSN号： 1000-8608

摘要： Metaphor is a natural phenomenon of the universal language.In the
   process of affective computing,the feelings of some sentences are
   aroused by the metaphor.Therefore,sentimental metaphor will affect the
   outcome of affective computing.Based on the theory of metaphor,from the
   perspective of machine learning,dominant metaphor identification of
   Chinese text is studied.The difference of areas between target domain
   and source domain is regarded as breakthrough point.Firstly,target
   domain and source domain are got using part of speech tagging and the
   interdependence parsing analysis;then,areas classifying and word
   similarity calculation are given;lastly,support vector machine is used
   so as to identify metaphor of sentence.This study will play a certain
   role in the automatic identification of metaphor and metaphorical
   understanding.

备注： 新增回溯数据