WLV-RIT at HASOC-Dravidian-CodeMix-FIRE2020: Offensive Language Identification in Code-switched YouTube Comments
This work addresses the problem of detecting offensive content in code-mixed social media data for Dravidian language communities, representing an incremental improvement in a specific shared task.
The paper tackled offensive language identification in code-switched Malayalam-English YouTube comments by applying cross-lingual contextual word embeddings and transfer learning, achieving a weighted average F1 score of 0.89 and ranking 5th out of 12 participants.
This paper describes the WLV-RIT entry to the Hate Speech and Offensive Content Identification in Indo-European Languages (HASOC) shared task 2020. The HASOC 2020 organizers provided participants with annotated datasets containing social media posts of code-mixed in Dravidian languages (Malayalam-English and Tamil-English). We participated in task 1: Offensive comment identification in Code-mixed Malayalam Youtube comments. In our methodology, we take advantage of available English data by applying cross-lingual contextual word embeddings and transfer learning to make predictions to Malayalam data. We further improve the results using various fine tuning strategies. Our system achieved 0.89 weighted average F1 score for the test set and it ranked 5th place out of 12 participants.