We present a novel dataset and model for a multilingual setting to approach the task of Joint Entity and Relation Extraction. The SMi-LER dataset consists of 1.1 M annotated sentences, representing 36 relations, and 14 languages. To the best of our knowledge, this is currently both the largest and the most comprehensive dataset of this type. We introduce HERBERTa, a pipeline that combines two independent BERT models: one for sequence classification, and the other for entity tagging. The model achieves micro F 1 81.49 for English on this dataset, which is close to the current SOTA on CoNLL, SpERT.

This paper presents a system used for SemEval-2021 Task 5: Toxic Spans Detection. Our system is an ensemble of BERT-based models for binary word classification, trained on a dataset extended by toxic comments modified and generated by two language models. For the toxic word classification, the prediction threshold value was optimized separately for every comment, in order to maximize the expected F1 value.