摘要
作文素材在小学语文作文辅助中的作用不可忽视。但当前存在的作文素材数量繁多却普遍缺乏个性化的推荐模式,极易引起小学生知识过载现象。作文素材的非结构化数据特征使得计算机对其存取操作过于复杂,进而会对数据的有效组织产生阻碍。通过对作文语料的文本自动摘要处理来去除冗余、提取文本中心内容,可以改善作文辅助中的信息过载问题以及素材语料中存在的大量冗余,对文本标签的获取产生干扰问题。在完善作文标签定义的前提下,提出一种基于文本自动摘要的小学语文作文标签提取方法。
The role of composition materials in primary school Chinese composition auxiliary cannot be ignored. However, there is a general lack of personalized recommendation mode in current composition materials, which easily leads to the phenomenon of knowledge overload of primary school students. The unstructured data features of the composition materials make it too complicated for computer to access operations, which will hinder the effective organization of the data. In order to improve the information overload in composition assistance and the interference of a large amount of redundancy in materials corpus on the acquisition of textual tags, this paper removed redundancy and extracted textual center content by automatically textual abstracting. On the premise of perfecting the definition of composition label, this paper presented a method of extracting primary school composition labels based on automatic text abstract.
作者
朱晓亮
吴逸尘
殷姿
Zhu Xiaoliang;Wu Yichen;Yin Zi(National Engineering Research Center for E-learning, Central China Normal University, Wuhan 430079, Hubei, China;National Engineering Laboratory for Educational Big Data, Central China Normal University, Wuhan 430079, Hubei, China)
出处
《计算机应用与软件》
北大核心
2019年第2期222-227,322,共7页
Computer Applications and Software
基金
国家重点研发计划项目(2018YFB1004500
2018YFB1004504)
湖北省技术创新专项重大项目(2017AKA191)
教育部人文社会科学研究规划基金项目(18YJAZH152)
