日文政治隐喻语料库构建方法  

A Method for Constructing a Japanese Political Metaphor Corpus

作　　者：朱毅[1] 李蔚然 刘棕楠 ZHU Yi;LI Weiran;LIU Zongnan(Dufl School of Software,Dalian University of Foreign Languages,Dalian 116044,China;School of Foreign Languages,Shenyang Ligong University,Shenyang 110158,China)

机构地区：[1]大连外国语大学软件学院,辽宁大连116044 [2]沈阳理工大学外国语学院,辽宁沈阳110158

出　　处：《现代信息科技》2024年第10期81-86,共6页Modern Information Technology

基　　金：2020年辽宁省教育科学“十三五”规划项目(JG20DB120)。

摘　　要：旨在构建专有日文政治隐喻语料库,解决目前针对日文政治语篇,成规模、高质量的政治隐喻语料资源匮乏、识别方式单一的问题。使用日本国会演说作为原始语料,制定一套完整的标注体系,并进一步对语料库进行统计分析。该语料库可论证政治隐喻在日文中同样被普遍使用,且种类多样。在此基础上,采用机器学习算法搭建识别模型进行实验。根据实验结果,该语料库可作为日文隐喻研究基础数据库,为后续日文政治隐喻的自动识别提供有力支撑。The paper aims to construct a proprietary Japanese political metaphor corpus,addressing the current problems of a lack of large-scale and high-quality political metaphor corpus resources and a single recognition method for Japanese political discourse.It uses speeches by the Japanese Congress as the original corpus,develops a complete labeling system,and further conducts statistical analysis on the corpus.This corpus can demonstrate that political metaphors are also widely used in Japanese and have a variety of types.On this basis,Machine Learning algorithms are used to construct recognition models for experiments.According to the experimental results,this corpus can serve as a basic database for Japanese metaphor research,providing strong support for the automatic recognition of Japanese political metaphor in the future.

关 键 词：政治隐喻 语料库 日语文本 自动识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] G353.1[自动化与计算机技术—计算机科学与技术]