English

From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection

Computation and Language 2021-02-25 v1 Machine Learning

Abstract

Natural language processing is a fast-growing field of artificial intelligence. Since the Transformer was introduced by Google in 2017, a large number of language models such as BERT, GPT, and ELMo have been inspired by this architecture. These models were trained on huge datasets and achieved state-of-the-art results on natural language understanding. However, fine-tuning a pre-trained language model on much smaller datasets for downstream tasks requires a carefully-designed pipeline to mitigate problems of the datasets such as lack of training data and imbalanced data. In this paper, we propose a pipeline to adapt the general-purpose RoBERTa language model to a specific text classification task: Vietnamese Hate Speech Detection. We first tune the PhoBERT on our dataset by re-training the model on the Masked Language Model task; then, we employ its encoder for text classification. In order to preserve pre-trained weights while learning new feature representations, we further utilize different training techniques: layer freezing, block-wise learning rate, and label smoothing. Our experiments proved that our proposed pipeline boosts the performance significantly, achieving a new state-of-the-art on Vietnamese Hate Speech Detection campaign with 0.7221 F1 score.

Keywords

Cite

@article{arxiv.2102.12162,
  title  = {From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection},
  author = {Quang Huu Pham and Viet Anh Nguyen and Linh Bao Doan and Ngoc N. Tran and Ta Minh Thanh},
  journal= {arXiv preprint arXiv:2102.12162},
  year   = {2021}
}

Comments

Published in 2020 12th International Conference on Knowledge and Systems Engineering (KSE)

R2 v1 2026-06-23T23:27:59.241Z