You are here:

Automatic Summary Grading on Narrative Article for English Learner
PROCEEDINGS

, , National Taiwan Normal University, Taiwan ; , Taipei Municipal Shilin High School of Commerce, Taiwan ; , National Taiwan Normal University, Taiwan

E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education, in Kona, Hawaii, United States Publisher: Association for the Advancement of Computing in Education (AACE), San Diego, CA

Abstract

The open questions about article's summarization can evaluate whether students understand the content of an article. However, it is a time-consuming task for teachers to give feedback and score. For solving this problem, we design a system to automatically grade the summarization questions on English narrative article without correct answer given by teachers. Accordingly, the students have more opportunities to practice with acquiring evaluation feedback in short time. In the proposed system, the article and the student's summary are represented by semantic graphs, which are compared to extract the matching features. Furthermore, the machine learning method is used to establish the grading classification model for the given summary. The experiment results show that the proposed method can achieve high overall precision when the articles have distinguishable words to express its focus.

Citation

Koh, J.L., Wang, H., Huang, C.Y. & Lee, G. (2015). Automatic Summary Grading on Narrative Article for English Learner. In Proceedings of E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education (pp. 823-830). Kona, Hawaii, United States: Association for the Advancement of Computing in Education (AACE). Retrieved September 21, 2020 from .

Keywords

Slides