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

Understand

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.