# Gauravarora@HASOC-Dravidian-CodeMix-FIRE2020: Pre-training ULMFiT on Synthetically Generated Code-Mixed Data for Hate Speech Detection

arXiv: https://arxiv.org/abs/2010.02094 · HTML: https://mlsanity.com/paper/2010.02094/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [A systematic review of Hate Speech automatic detection using Natural Language Processing](https://mlsanity.com/paper/2106.00742/) (2021)
- [indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages](https://mlsanity.com/paper/2102.07150/) (2021)
- [Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Posts](https://mlsanity.com/paper/2108.10939/) (2021)
- [Developing Successful Shared Tasks on Offensive Language Identification for Dravidian Languages](https://mlsanity.com/paper/2111.03375/) (2021)
- [Optimize_Prime@DravidianLangTech-ACL2022: Abusive Comment Detection in Tamil](https://mlsanity.com/paper/2204.09675/) (2022)

## Abstract (arXiv)

This paper describes the system submitted to Dravidian-Codemix-HASOC2020: Hate Speech and Offensive Content Identification in Dravidian languages (Tamil-English and Malayalam-English). The task aims to identify offensive language in code-mixed dataset of comments/posts in Dravidian languages collected from social media. We participated in both Sub-task A, which aims to identify offensive content in mixed-script (mixture of Native and Roman script) and Sub-task B, which aims to identify offensive content in Roman script, for Dravidian languages. In order to address these tasks, we proposed pre-training ULMFiT on synthetically generated code-mixed data, generated by modelling code-mixed data generation as a Markov process using Markov chains. Our model achieved 0.88 weighted F1-score for code-mixed Tamil-English language in Sub-task B and got 2nd rank on the leader-board. Additionally, our model achieved 0.91 weighted F1-score (4th Rank) for mixed-script Malayalam-English in Sub-task A and 0.74 weighted F1-score (5th Rank) for code-mixed Malayalam-English language in Sub-task B.