基于话题决策模型的英文文本切题度计算方法研究  

Research on the Calculation Method of English Text Relevance Based on Topic Decision Model

作　　者：胡婷[1] HU Ting(Xi'an Jiaotong University City College,Xi'an 710018 China)

机构地区：[1]西安交通大学城市学院,陕西西安710018

出　　处：《自动化技术与应用》2024年第4期60-62,98,共4页Techniques of Automation and Applications

摘　　要：为了对英文作文考试中英文文本的切题度加以判断,提出一套基于话题决策模型的英文文本切题度计算方法。介绍该算法的数据处理流程与话题决策模型的数据处理方法,最后通过WIKI_727K数据集对话题决策模型进行训练与测试,经实验研究发现,所提出的话题决策模型在精确率、召回率等方面具有一定的应用优势,并在ASAP数据集上表现出较为理想的切题度判断效果。In order to judge the relevance of English text in English composition examination,this paper proposes a set of English text relevance calculation method based on topic decision model,and introduces the data processing flow of the algorithm and the data processing method of topic decision model in detail.Finally,through WIKI_727K data set trains and tests the topic decision-making model.Through experimental research,it is found that the topic decision-making model proposed in this study has certain application advantages in accuracy and recall,and shows an ideal effect of relevance judgment on ASAP data set.

关 键 词：英文文本 切题度 话题决策模型 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]