Automated essay scoring using efficient transformer-based language models
This work addresses computational efficiency for educators and researchers using automated essay scoring, but it is incremental as it builds on existing transformer-based methods.
The paper tackled the problem of high computational costs in automated essay scoring by challenging the notion that larger models are always better, achieving excellent results with fewer parameters through ensembling of fine-tuned pretrained models.
Automated Essay Scoring (AES) is a cross-disciplinary effort involving Education, Linguistics, and Natural Language Processing (NLP). The efficacy of an NLP model in AES tests it ability to evaluate long-term dependencies and extrapolate meaning even when text is poorly written. Large pretrained transformer-based language models have dominated the current state-of-the-art in many NLP tasks, however, the computational requirements of these models make them expensive to deploy in practice. The goal of this paper is to challenge the paradigm in NLP that bigger is better when it comes to AES. To do this, we evaluate the performance of several fine-tuned pretrained NLP models with a modest number of parameters on an AES dataset. By ensembling our models, we achieve excellent results with fewer parameters than most pretrained transformer-based models.