• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.121-122
• /
• 2012

컴퓨터를 사용한 서술형 답안의 자동채점은 채점의 편의성과 객관성을 제고하기 위하여 많은 연구자들이 연구해 왔으며 자동채점의 성능을 향상시키기 위해 여러 가지 방법들이 제안되었다. 본 논문은 서술어 정규화를 통하여 서술형 답안의 자동채점 정확도를 높이고자 하였다. 기존의 다른 채점 방법들과 비교했을때 서술어 정규화 기법을 적용한 채점 방식은 기존의 방법들보다 유사도 계산 정확도가 향상되어 정답 판별 정확도가 향상되는 것을 확인할 수 있었다. 서술어 정규화는 기존의 모든 서술형 답안 채점 방법에 추가적으로 적용할 수 있는 범용성을 가지고 있다. 따라서 서술어 정규화는 기존 방법들의 자동채점 정확도를 향상시켜 보다 정확하게 서술형 답안을 채점할 수 있다.

• The Journal of Korean Association of Computer Education
• /
• v.21 no.6
• /
• pp.105-115
• /
• 2018

The descriptive-type question is appropriate for deep thinking ability evaluation, but it is not easy to grade. Since, even though same grading criterion, the graders produce different scores, we need the objective evaluation system. However, the system needs the Korean analysis. As the descriptive-type answering is described with the compound sentence, the system has to analyze the compound sentence. This paper develops the Korean syntactic-semantic analysis system for compound sentence and evaluates performance of the system. This system selects the modifiee of the word phrase using syntactic-semantic constraint and semantic dictionary. The 93% accurate rate shows that the system is effective. This system will be utilized in descriptive-type grading and Korean processing.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.8
• /
• pp.17-25
• /
• 2013

TIn this paper, we propose a model automatically scoring a student's answer for a descriptive problem by using a voting method. Considering the model construction cost, the proposed model does not separately construct the automatic scoring model per problem type. In order to utilize features useful for automatically scoring the descriptive answers, the proposed model extracts feature values from the results, generated by comparing the student's answer with the answer sheet. For the purpose of improving the precision of the scoring result, the proposed model collects the scoring results classified by a few machine learning based classifiers, and unanimously selects the scoring result as the final result. Experimental results show that the single machine learning based classifier C4.5 takes 83.00% on precision while the proposed model improve the precision up to 90.57% by using three machine learning based classifiers C4.5, ME, and SVM.

• Journal of Elementary Mathematics Education in Korea
• /
• v.18 no.2
• /
• pp.297-318
• /
• 2014

This study is designed for helping elementary school teachers have an insight into making or choosing questions of descriptive assessment in mathematics. For this, it is analyzed 30 descriptive mathematical questions produced by Gyeonggi Provincial Office of Education in 2011 and 2012 and 3rd to 6th grade students' papers marked by their teachers in charge from 2 elementary schools located in Gyeonggi Province. The main focus of analysis is the errors of students' answers and teachers' marking not from their own mistakes but from the defects of questions themselves. As a result of analysis, 7 cases of problematic situations are induced and they are reorganized into 3 categories as follow: i) case of not performing unique purpose of descriptive assessment, ii) case of inducing the problem of fairness of grading, iii) case of leading students erroneous direction.

• The Mathematical Education
• /
• v.63 no.2
• /
• pp.187-207
• /
• 2024

In this study, we explored the feasibility of automatically scoring descriptive assessment items using GPT-4 based ChatGPT by comparing and analyzing the scoring results between teachers and GPT-4 based ChatGPT. For this purpose, three descriptive items from the permutation and combination unit for first-year high school students were selected from the KICE (Korea Institute for Curriculum and Evaluation) website. Items 1 and 2 had only one problem-solving strategy, while Item 3 had more than two strategies. Two teachers, each with over eight years of educational experience, graded answers from 204 students and compared these with the results from GPT-4 based ChatGPT. Various techniques such as Few-Shot-CoT, SC, structured, and Iteratively prompts were utilized to construct prompts for scoring, which were then inputted into GPT-4 based ChatGPT for scoring. The scoring results for Items 1 and 2 showed a strong correlation between the teachers' and GPT-4's scoring. For Item 3, which involved multiple problem-solving strategies, the student answers were first classified according to their strategies using prompts inputted into GPT-4 based ChatGPT. Following this classification, scoring prompts tailored to each type were applied and inputted into GPT-4 based ChatGPT for scoring, and these results also showed a strong correlation with the teachers' scoring. Through this, the potential for GPT-4 models utilizing prompt engineering to assist in teachers' scoring was confirmed, and the limitations of this study and directions for future research were presented.

• Journal of Korean Home Economics Education Association
• /
• v.32 no.3
• /
• pp.135-159
• /
• 2020

The purpose of this study was to develop items of an essay response assessment that could align with the instructions and assessments in the high school home economics curriculum. The contents of the study were as follows. First, to establish an assessment plan, 14 achievement standards were analyzed in the assessment area, and the elements of the questions were developed including the content elements of a total of 29 questions. Second, to develop the assessment tools, preliminary questions suited to the structure of essay questions were developed, and the method of presenting data and scoring criteria to be utilized in the questions was selected. Third, to prepare the answers and the scoring criteria tables, the answers to the sample questions for each score were prepared in form of a scoring criteria table, and the objectives of the assessment, the scoring items, and the scores for each item were reviewed. Fourth, the developed questions and answers were revised and supplemented by teachers of the professional learning community through preliminary and mutual review on the components of the questions, the embodiment of the assessment objectives, the implementation of the assessment intent, and the grading. This study can be used as a foundational study for the development of essay-type questions and scoring criteria in essay assessment in the field of education. Furthermore, the results of this study could help teachers enhance their learners' ability to apply knowledge in the future.

• Journal of The Korean Association For Science Education
• /
• v.36 no.3
• /
• pp.389-397
• /
• 2016

This study aims to test the efficacy of English-based automated computer scoring models and machine translation to score Korean college students' written responses on natural selection concept items. To this end, I collected 128 pre-service biology teachers' written responses on four-item instrument (total 512 written responses). The machine translation software (i.e., Google Translate) translated both original responses and spell-corrected responses. The presence/absence of five scientific ideas and three $na{\ddot{i}}ve$ ideas in both translated responses were judged by the automated computer scoring models (i.e., EvoGrader). The computer-scored results (4096 predictions) were compared with expert-scored results. The results illustrated that no significant differences in both average scores and statistical results using average scores was found between the computer-scored result and experts-scored result. The Pearson correlation coefficients of composite scores for each student between computer scoring and experts scoring were 0.848 for scientific ideas and 0.776 for $na{\ddot{i}}ve$ ideas. The inter-rater reliability indices (Cohen kappa) between computer scoring and experts scoring for linguistically simple concepts (e.g., variation, competition, and limited resources) were over 0.8. These findings reveal that the English-based automated computer scoring models and machine translation can be a promising method in scoring Korean college students' written responses on natural selection concept items.

• Journal of The Korean Association For Science Education
• /
• v.25 no.2
• /
• pp.173-183
• /
• 2005

In this study, we questioned what assessment types and scoring methods of science performance assessment(SPA) were being used in middle and high school, and how much these SPA scores were reliable(generalizable). To answer these questions, SPA data obtained from the seven schools were classified according to assessment type and scoring method. Based upon this classification, we analyzed the reliability by applying generalizability theory. The result, from the classification of assessment type and scoring method, showed that SPA types of the seven schools were divided into two types: paper-pencil type and task type. Paper-pencil type included answer(content)-restricted essay-type test solely. Task type has two parts: process and outcome assessment. As the results of analyzing scoring methods of the seven schools, there were two cases in the way of scoring methods: one case is scoring all essay-type items and performance tasks by one teacher, the other is scoring assigned performance tasks by two teachers. But the case of scoring assigned essay-type items or the case of cross scoring by two or more teachers were not found. The findings of the reliability analysis are as follows: (1) Effect of essay-type item to SPA score was larger than that of performance task. (2) There was remarkable difference among the seven schools' interaction effect of person and rater in scoring performance tasks. (3) Most of generalizability(reliability) coefficients of SPA for the seven schools were smaller than the acceptable generalizability coefficient(0.80). Therefore, the population of statistical parameters such as number of item, task and rater, should be increased for approaching the acceptable generalizability level.

• Communications of Mathematical Education
• /
• v.28 no.4
• /
• pp.553-571
• /
• 2014

Mathematical process is an issue in current mathematics education. In this paper discuss how to assess the mathematical process using essay type questions. For this we first suggest the concept of Mathematical Process Oriented Question which is an essay type question and possible to assess mathematical processes, that is, the mathematical communication, reasoning, and problem solving as well as mathematics knowledge. And we develop a framework for developing the mathematical process oriented question and rubric, examples of assessment standards and those questions containing rubric for assessing mathematical processes. The results of this paper can serve as basic data and examples for follow up research about mathematical process assessment.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.109-110
• /
• 2023

본 논문에서는 교육현장에서 서술평평가를 자동화하기 위한 시스템을 제안한다. 제안 시스템은 장문의 응답에서 단어를 추출하여 단어 간 네트워크를 생성하고 정답 네트워크와 비교를 통해 평가를 실시한다. 기존의 키워드 방식은 네트워크 관점에서 노드를 기준으로 채점하는 것이라면, 제안 시스템은 엣지를 기준으로 채점하게 되어 학습자의 답변에서 지식의 관계성을 채점할 수 있어 학습자에게 유용한 피드백을 줄 수 있을 것으로 기대한다.