|
--- |
|
language: mr |
|
license: cc-by-4.0 |
|
datasets: |
|
- L3Cube-MahaHate |
|
widget: |
|
- text: "I like you. </s></s> I love you." |
|
--- |
|
|
|
|
|
## MahaHate-BERT |
|
|
|
MahaHate-BERT (Marathi Hate speech identification) is a MahaBERT(l3cube-pune/marathi-bert) model fine-tuned on L3Cube-MahaHate - a Marathi tweet-based hate speech detection dataset. This is a two-class model with labels as hate (LABEL_1) and not (LABEL_0). The 4-class model can be found <a href='https://huggingface.co/l3cube-pune/mahahate-multi-roberta'> here </a> |
|
|
|
[dataset link] (https://github.com/l3cube-pune/MarathiNLP) |
|
|
|
More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2203.13778) |
|
|
|
``` |
|
@inproceedings{patil2022l3cube, |
|
title={L3Cube-MahaHate: A Tweet-based Marathi Hate Speech Detection Dataset and BERT Models}, |
|
author={Patil, Hrushikesh and Velankar, Abhishek and Joshi, Raviraj}, |
|
booktitle={Proceedings of the Third Workshop on Threat, Aggression and Cyberbullying (TRAC 2022)}, |
|
pages={1--9}, |
|
year={2022} |
|
} |
|
``` |
