基于向量空间模型的对外汉语应用文写作词汇分类系统研究  

Study on VSM⁃based vocabulary classification system of TCFL practical writing

作　　者：马艳荣 温煜坤 MA Yanrong;WEN Yukun(Xi’an Traffic Engineering Institute,Xi’an 710300,China;Inner Mongolia Normal University,Hohhot 010022,China)

机构地区：[1]西安交通工程学院,陕西西安710300 [2]内蒙古师范大学,内蒙古呼和浩特010022

出　　处：《现代电子技术》2021年第8期137-140,共4页Modern Electronics Technique

基　　金：国家自然科学基金项目(50901039);陕西省教育厅专项科研项目(17JK1013)。

摘　　要：为了解决传统对外汉语应用文写作词汇分类系统存在分类精度低、运行空间占用过大的问题,提出基于向量空间模型的对外汉语应用文写作词汇分类系统。首先,分析系统功能,对外汉语应用文写作词汇分类系统的主要功能为训练与词汇判定。根据上述的分析结果,明确分类系统的大致程序,并构建系统的总体结构。其次,设计系统的硬件与软件,硬件部分主要包括词汇训练模块、特征权重计算模块以及词汇分类模块。软件部分计算词汇特征权重值,并基于向量空间模型完成对外汉语应用文写作词汇的分类。最后,进行验证实验。实验结果表明,与传统的词汇分类系统相比,基于向量空间模型的分类系统具有更高的分类精度,并且运行空间占用明显缩小。As the traditional vocabulary classification system of TCFL(teaching Chinese as a foreign language)practical writing has low classification accuracy and large running space occupation,a VSM(vector space model)based vocabulary classification system of TCFL practical writing is proposed.The system function is analyzed,and main functions of the vocabulary classification system of TCFL practical writing are training and vocabulary judgment.According to the above analysis results,the general procedure of the classification system is defined,and the overall structure of the system is constructed.The hardware and software of the system are designed.The hardware part is mainly composed of the vocabulary training module,feature weight calculation module and vocabulary classification module.In the software part,the feature weight value of vocabulary is calculated,and the vocabulary classification of TCFL practical writing is completed based on VSM.The verification experiment is carried out.The experimental results show that in comparison with the traditional vocabulary classification system,the VSM based classification system has higher classification accuracy,and the running space occupation is reduced significantly.

关 键 词：对外汉语 应用文写作 词汇分类 向量空间模型 特征权重计算 系统设计 

分 类 号：TN911-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]