ASAG2024
ASAG2024 is a comprehensive short‑answer grading benchmark dataset created by the Zurich University of Applied Sciences. It comprises seven commonly used short‑answer grading datasets, totaling 19,000 question‑answer‑score triples across multiple subjects and education levels. Scores are normalized between 0 and 1 to facilitate comparison across datasets. The creation involved integrating data from multiple sources and standardizing them. The dataset is primarily used to evaluate and compare the performance of automated grading systems, aiming to address automation and generalizability challenges in short‑answer grading.
Dataset description and usage context
ASAG2024 Dataset Overview
Dataset Description
- Name: ASAG2024
- Tags: ASAG, Grading
- Size: 10K < n < 100K
- Language: English
- Creator: Gérôme Meyer
- License: Data source license applies (see below)
Data Source
The dataset was collected from the following source:
-
Source: Stita
-
Repository: https://github.com/edgresearch/dataset-automaticgrading-2022/tree/master
-
Citation:
del Gobbo, E., Guarino, A., Cafarelli, B. et al. GradeAid: a framework for automatic short answers grading in educational contexts—design, implementation and evaluation. Knowl Inf Syst 65, 4295–4334 (2023). https://doi.org/10.1007/s10115-023-01892-9
Dataset Content
The dataset contains the following elements:
- Questions
- Reference answers
- Student answers
- Human scores
Dataset Authors
- Gérôme Meyer
- Philip Breuer
Contact Information
- Email: gerome.meyer@pm.me
News
- [May 12 2024] ⏰ Reorganizing code, materials and dataset.
- [Nov 26 2024] 🎉 Paper published on arXiv.
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.