日文政治隐喻语料库构建方法

A Method for Constructing a Japanese Political Metaphor Corpus

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.