Automate Descriptive Answer Grading using Reference based Models

2022 OITS International Conference on Information Technology (OCIT) Pub Date : 2022-12-01 DOI:10.1109/OCIT56763.2022.00057

M. Sayeed, Deepa Gupta

{"title":"Automate Descriptive Answer Grading using Reference based Models","authors":"M. Sayeed, Deepa Gupta","doi":"10.1109/OCIT56763.2022.00057","DOIUrl":null,"url":null,"abstract":"Global universities are establishing institutional setups that offer a hybrid format of education. The next step of education is to maintain quality and flexibility, such as providing the option to convert online courses such as Massive Open Online Courses (MOOCS) to course credits. However, several universities are reluctant to completely transition to online-based education due to poor digital experience in educational tools. The available evaluation tools such as Multiple-choice answers (MCQ) aren't able to evaluate students holistically. In this study, research work aims for an improvised reference-based approach (utilizing student and reference answers) that evaluates descriptive answers with the Siamese architecture- Roberta bi-encoder based transformer models for Automated Short Answer Grading (ASAG). The architecture was designed considering ASAG tasks constrained to feasible compute resources. The research work presents the competitive performance of the models, further improvised with finetuning and hyperparameter optimization process on the benchmark SemEval-2013 2way task dataset.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 OITS International Conference on Information Technology (OCIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/OCIT56763.2022.00057","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

Abstract

Global universities are establishing institutional setups that offer a hybrid format of education. The next step of education is to maintain quality and flexibility, such as providing the option to convert online courses such as Massive Open Online Courses (MOOCS) to course credits. However, several universities are reluctant to completely transition to online-based education due to poor digital experience in educational tools. The available evaluation tools such as Multiple-choice answers (MCQ) aren't able to evaluate students holistically. In this study, research work aims for an improvised reference-based approach (utilizing student and reference answers) that evaluates descriptive answers with the Siamese architecture- Roberta bi-encoder based transformer models for Automated Short Answer Grading (ASAG). The architecture was designed considering ASAG tasks constrained to feasible compute resources. The research work presents the competitive performance of the models, further improvised with finetuning and hyperparameter optimization process on the benchmark SemEval-2013 2way task dataset.

查看原文本刊更多论文

使用基于参考的模型自动描述答案评分

全球大学正在建立提供混合教育形式的机构设置。教育的下一步是保持质量和灵活性，例如提供将在线课程(如大规模在线开放课程(MOOCS))转换为课程学分的选项。然而，由于教育工具的数字化经验不足，一些大学不愿意完全过渡到在线教育。现有的评估工具，如选择题(MCQ)，并不能全面地评估学生。在这项研究中，研究工作的目的是建立一种基于参考的临时方法(利用学生和参考答案)，用Siamese架构- Roberta基于双编码器的自动简短答案评分(ASAG)变压器模型来评估描述性答案。该体系结构的设计考虑了ASAG任务对可行计算资源的约束。研究工作展示了模型的竞争性能，并在基准SemEval-2013双向任务数据集上进一步进行了微调和超参数优化过程。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2022 OITS International Conference on Information Technology (OCIT)

自引率

0.00%

发文量