The SemEval 2021 task 5: Toxic Spans Detection is a task of identifying considered-toxic spans in text, which provides a valuable, automatic tool for moderating online contents. This paper represents the second-place method for the task, an ensemble of two approaches. While one approach relies on combining different embedding methods to extract diverse semantic and syntactic representations of words in context; the other utilizes extra data with a slightly customized Self-training, a semi-supervised learning technique, for sequence tagging problems. Both of our architectures take advantage of a strong language model, which was fine-tuned on a toxic classification task. Although experimental evidence indicates higher effectiveness of the first approach than the second one, combining them leads to our best results of 70.77 F1-score on the test dataset.

This paper proposes an improved custom model for WNUT task 2: Identification of Informative COVID-19 English Tweet. We improve experiment with the effectiveness of fine-tuning methodologies for state-of-the-art language model RoBERTa. We make a preliminary instantiation of this formal model for the text classification approaches. With appropriate training techniques, our model is able to achieve 0.9218 F1-score on public validation set and the ensemble version settles at top 9 F1-score (0.9005) and top 2 Recall (0.9301) on private test set.