首页> 外文OA文献 >EssayCritic: A Computer-Supported English Essay Critiquing System using Latent Semantic Analysis
【2h】

EssayCritic: A Computer-Supported English Essay Critiquing System using Latent Semantic Analysis

机译:EssayCritic:一种使用潜在语义分析的计算机支持英语论文评论系统

摘要

The talk presents the EssayCritic system and discusses two recent applications (English composition teaching at HKBU and at Norwegian high school). The EssayCritic makes use of Latent Semantic Analysis (LSA) to compute feedback on student essays. LSA is both a theory of text comprehension and a mathematical technique for comparing two segments of text, one input by students and the other collected and stored by domain experts (e.g. teachers). We describe the components of the system and explain the workings of LSA. Then we present findings from the Norway study (recently completed). The studies differ in that the HK trials were organized with one student per computer, whereas in Norway the students were grouped in pairs, reflecting local teaching styles. Preliminary findings reveal distinct modes of writing (writing, feedback, reflection, revision) for both settings and patterns of working in pairs in the other. Based on the findings we develop a conceptual framework for collaborative essay writing that integrates concepts from design theory (e.g. reflection-in-action) and communication theory (e.g. inter-subjectivity, common ground). Our goals are to understand and characterize collaborative essay writing as a design activity and to provide computational support for it.
机译:演讲介绍了EssayCritic系统,并讨论了两个最近的应用程序(在浸大和挪威高中进行英语作文教学)。 EssayCritic利用潜在语义分析(LSA)来计算学生论文的反馈。 LSA既是一种文本理解理论,又是一种用于比较文本的两个部分的数学技术,一个部分是学生输入的,另一部分是领域专家(例如教师)收集和存储的。我们描述了系统的组件并解释了LSA的工作原理。然后,我们介绍挪威研究的结果(最近完成)。这些研究的不同之处在于,香港的试验是每台计算机由一名学生组织的,而在挪威,这些学生是成对分组的,反映了当地的教学风格。初步调查结果揭示了在成对工作中的设置和模式的不同写作模式(写作,反馈,反思,修订)。基于这些发现,我们开发了一个用于合作论文写作的概念框架,该框架将设计理论(例如行动中的反思)和传播理论(例如主体间性,共同点)的概念整合在一起。我们的目标是将协作论文写作理解为工作中的特征并将其表征为设计活动,并为此提供计算支持。

著录项

  • 作者

    Morch A;

  • 作者单位
  • 年度 2007
  • 总页数
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类

相似文献

  • 外文文献
  • 中文文献
  • 专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号