Automatic Short Answer Grading via Multiway Attention Networks
This work addresses the challenge of grading open-ended student answers across domains for K-12 education, offering a cost-effective solution to reduce teacher workloads, though it appears incremental in method.
The paper tackles the problem of automatic short answer grading (ASAG) by proposing a multiway attention network framework to extract linguistic information and model semantic relations between student and reference answers, achieving state-of-the-art performance on a large real-world K-12 dataset.
Automatic short answer grading (ASAG), which autonomously score student answers according to reference answers, provides a cost-effective and consistent approach to teaching professionals and can reduce their monotonous and tedious grading workloads. However, ASAG is a very challenging task due to two reasons: (1) student answers are made up of free text which requires a deep semantic understanding; and (2) the questions are usually open-ended and across many domains in K-12 scenarios. In this paper, we propose a generalized end-to-end ASAG learning framework which aims to (1) autonomously extract linguistic information from both student and reference answers; and (2) accurately model the semantic relations between free-text student and reference answers in open-ended domain. The proposed ASAG model is evaluated on a large real-world K-12 dataset and can outperform the state-of-the-art baselines in terms of various evaluation metrics.