NLPBK at VLSP-2020 shared task: Compose transformer pretrained models for Reliable Intelligence Identification on Social network
This addresses the problem of identifying reliable intelligence on Vietnamese social networks, but it is incremental as it adapts existing transformer models with metadata.
The authors tackled reliable intelligence identification on Vietnamese social networks by combining BERT-base pretrained models with metadata features like comments and likes, achieving 0.9392 ROC-AUC on a public test set and ranking top 2 with 0.9513 ROC-AUC on a private test set.
This paper describes our method for tuning a transformer-based pretrained model, to adaptation with Reliable Intelligence Identification on Vietnamese SNSs problem. We also proposed a model that combines bert-base pretrained models with some metadata features, such as the number of comments, number of likes, images of SNS documents,... to improved results for VLSP shared task: Reliable Intelligence Identification on Vietnamese SNSs. With appropriate training techniques, our model is able to achieve 0.9392 ROC-AUC on public test set and the final version settles at top 2 ROC-AUC (0.9513) on private test set.