Leveraging Transfer Learning for Reliable Intelligence Identification on Vietnamese SNSs (ReINTEL)

TL;DR

This paper explores transformer-based models, including monolingual and multilingual pre-trained ones, combined with ensemble methods, to enhance reliable intelligence detection on Vietnamese social networks, achieving high ROC-AUC scores.

Contribution

It introduces transformer-based approaches and ensemble techniques specifically tailored for Vietnamese SNSs, demonstrating competitive performance in intelligence identification.

Findings

Achieved ROC-AUC of 0.9378 on private test set

Utilized both monolingual and multilingual pre-trained models

Ensemble methods improved robustness and performance

Abstract

This paper proposed several transformer-based approaches for Reliable Intelligence Identification on Vietnamese social network sites at VLSP 2020 evaluation campaign. We exploit both of monolingual and multilingual pre-trained models. Besides, we utilize the ensemble method to improve the robustness of different approaches. Our team achieved a score of 0.9378 at ROC-AUC metric in the private test set which is competitive to other participants.