Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection
Paper β’ 2012.15761 β’ Published
How to use facebook/roberta-hate-speech-dynabench-r4-target with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="facebook/roberta-hate-speech-dynabench-r4-target") # Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("facebook/roberta-hate-speech-dynabench-r4-target")
model = AutoModelForSequenceClassification.from_pretrained("facebook/roberta-hate-speech-dynabench-r4-target")The R4 Target model from Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection
@inproceedings{vidgen2021lftw,
title={Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection},
author={Bertie Vidgen and Tristan Thrush and Zeerak Waseem and Douwe Kiela},
booktitle={ACL},
year={2021}
}
Thanks to Kushal Tirumala and Adina Williams for helping the authors put the model on the hub!