面向领域的网页文本校对方法  

Domain-Oriented Web Text Proofreading Method

作　　者：田莎 刘晓强[1] 李柏岩[1] TIAN Sha;LIU Xiaoqiang;LI Baiyan(College of Computer Science and Technology,Donghua University,Shanghai 201620)

机构地区：[1]东华大学计算机科学与技术学院,上海201620

出　　处：《计算机与数字工程》2024年第6期1788-1794,共7页Computer & Digital Engineering

摘　　要：随着网络技术的快速发展,网站越来越成为各个机构发布和管理信息必不可少的渠道,用户也习惯使用浏览网页的方式去获取信息。随着公开信息量急剧增长,文本编辑和校对过程中难免会存在一些错误,自动文本校对是一个必要的辅助手段。目前针对文本编辑错误的研究较多,已有一些工具可以支持,但知识表述错误涉及具体的领域知识和语义关系,普通校对工具无法胜任。论文重点针对知识表述错误类的文本校对进行研究,提出一种基于知识图谱的面向领域知识的文本校对方法,论述了领域知识图谱的构建方法与流程、待校对文本的知识抽取方法以及基于知识图谱的校对方法。实验结果显示,该方法能够检测出网页中的语义错误,弥补通用检测工具的不足。Websites have increasingly become indispensable channels for various institutions to publish information,and us-ers are also accustomed to obtain information through browsing the web pages.With the rapid increase in the amount of public infor-mation,there are inevitably some errors in the process of text editing and proofreading.Automatic text proofreading is a necessary auxiliary means.At present,there are many studies and tools for text editing errors proofreading.However,it is difficult to find knowledge representation errors due to lacking specific domain knowledge and semantic relationships.This paper focuses on the re-search on text proofreading of knowledge representation errors,and proposes a domain knowledge-oriented text proofreading method based on knowledge graph.Experimental results show that this method can detect semantic errors in web pages and extend the gener-al text proofreading tools.

关 键 词：面向领域 文本校对 知识图谱 关键词提取 知识表述 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]