# LT@Helsinki at SemEval-2020 Task 12: Multilingual or language-specific BERT?

arXiv: https://arxiv.org/abs/2008.00805 · HTML: https://mlsanity.com/paper/2008.00805/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [MUDES: Multilingual Detection of Offensive Spans](https://mlsanity.com/paper/2102.09665/) (2021)
- [A systematic review of Hate Speech automatic detection using Natural Language Processing](https://mlsanity.com/paper/2106.00742/) (2021)
- [Multilingual Offensive Language Identification for Low-resource Languages](https://mlsanity.com/paper/2105.05996/) (2021)

## Abstract (arXiv)

This paper presents the different models submitted by the LT@Helsinki team for the SemEval 2020 Shared Task 12. Our team participated in sub-tasks A and C; titled offensive language identification and offense target identification, respectively. In both cases we used the so-called Bidirectional Encoder Representation from Transformer (BERT), a model pre-trained by Google and fine-tuned by us on the OLID and SOLID datasets. The results show that offensive tweet classification is one of several language-based tasks where BERT can achieve state-of-the-art results.