Learning Distributed Representations and Deep Embedded Clustering of Texts

Instructors face significant time and effort constraints when grading students’ assessments on a large scale. Clustering similar is unique effective technique that has the potential to significantly reduce workload of instructors in online large-scale learning environments. By grouping together assessments, marking one assessment cluster can be scaled other allowing for more efficient streamlined process. To address this issue, paper focuses text proposes method reducing by clustering assessments. The proposed involves use distributed representation transform texts into vectors, contrastive improve distinguishes differences among texts. presents general framework includes label representation, K-means, self-organization map algorithms, with objective improving performance using Accuracy (ACC) Normalized Mutual Information (NMI) metrics. evaluated experimentally two real datasets. results show maps K-means algorithms Pre-trained language models outperform different