Detecting Generated Scientific Papers using an Ensemble of Transformer Models
Computation and Language
2022-10-18 v1 Artificial Intelligence
Machine Learning
Abstract
The paper describes neural models developed for the DAGPap22 shared task hosted at the Third Workshop on Scholarly Document Processing. This shared task targets the automatic detection of generated scientific papers. Our work focuses on comparing different transformer-based models as well as using additional datasets and techniques to deal with imbalanced classes. As a final submission, we utilized an ensemble of SciBERT, RoBERTa, and DeBERTa fine-tuned using random oversampling technique. Our model achieved 99.24% in terms of F1-score. The official evaluation results have put our system at the third place.
Cite
@article{arxiv.2209.08283,
title = {Detecting Generated Scientific Papers using an Ensemble of Transformer Models},
author = {Anna Glazkova and Maksim Glazkov},
journal= {arXiv preprint arXiv:2209.08283},
year = {2022}
}
Comments
Accepted to SDP 2022 (Third Workshop on Scholarly Document Processing collocated with COLING 2022)