ASAGeR: Automated Short Answer Grading Regressor via Sentence Simplification

Mohammad Iqbal, Rosita Laili Udhiah, Tsamarah Rana Nugraha, Hsing Kuo Pao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

We propose an automated short answer grading system (ASAG) to estimate the student answer scores via text summarization from LLMs. The step of text summarization provides enough question answer normalization so that the summarized answers have the answer keys well organized and the grading based on that should be more accurate and easier than before, no matter the answers are graded by human or automatic graders. On the other hand, we also discuss the scenario when more than one grader are involved in the grading but providing inconsistent scores. We adopt a majority voting mechanism to overcome such difficulty and produce superior result in average. Overall the proposed methodology has its evaluation done to show the superiority to other state-of-the-art methods. The pre-trained transformer version 3.5 (GPT 3.5) is used to serve the text summarization tool given a well-designed prompt.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Knowledge Graph, ICKG 2023
EditorsVictor S. Sheng, Chindo Hicks, Charles Ling, Vijay Raghavan, Xindong Wu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages60-68
Number of pages9
ISBN (Electronic)9798350307092
DOIs
Publication statusPublished - 2023
Event14th IEEE International Conference on Knowledge Graph, ICKG 2023 - Hybrid, Shanghai, China
Duration: 1 Dec 20232 Dec 2023

Publication series

NameProceedings - IEEE International Conference on Knowledge Graph, ICKG 2023

Conference

Conference14th IEEE International Conference on Knowledge Graph, ICKG 2023
Country/TerritoryChina
CityHybrid, Shanghai
Period1/12/232/12/23

Keywords

  • Answer Grading
  • Natural Language Processing
  • Regression
  • Text Simplification

Fingerprint

Dive into the research topics of 'ASAGeR: Automated Short Answer Grading Regressor via Sentence Simplification'. Together they form a unique fingerprint.

Cite this