Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathi

Abstract

The widespread presence of offensive language on social media motivated the development of systems capable of recognizing such content automatically.Apart from a few notable exceptions, most research on automatic offensive language identification has dealt with English.To address this shortcoming, we introduce MOLD 1 , the Marathi Offensive Language Dataset.MOLD is the first dataset of its kind compiled for Marathi, thus opening a new domain for research in lowresource Indo-Aryan languages.We present results from several machine learning experiments on this dataset, including zero-short and other transfer learning experiments on state-ofthe-art cross-lingual transformers from existing data in Bengali, English, and Hindi.