# NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer

arXiv: https://arxiv.org/abs/2008.01354 · HTML: https://mlsanity.com/paper/2008.01354/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://mlsanity.com/paper/2305.04446/) (2023)
- [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)
- [Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages](https://mlsanity.com/paper/2210.11359/) (2022)
- [Offensive Hebrew Corpus and Detection using BERT](https://mlsanity.com/paper/2309.02724/) (2023)
- [LAHM : Large Annotated Dataset for Multi-Domain and Multilingual Hate Speech Identification](https://mlsanity.com/paper/2304.00913/) (2023)
- [A Systematic Survey of Natural Language Processing for the Greek Language](https://mlsanity.com/paper/2407.09861/) (2024)

## Abstract (arXiv)

This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual transfer with data selection. Leveraging the semi-supervised dataset resulted in performance improvements compared to the baseline trained solely with the manually-annotated dataset. We propose a new metric, Translation Embedding Distance, to measure the transferability of instances for cross-lingual data selection. We also introduce various preprocessing steps tailored for social media text along with methods to fine-tune the pre-trained multilingual BERT (mBERT) for offensive language identification. Our multilingual systems achieved competitive results in Greek, Danish, and Turkish at OffensEval 2020.