We generate counterspeech using three datasets and observe significant improvement across different attribute scores.
To enable more targeted diagnostic insights of such multilingual hate speech models, we introduce a set of functionalities for the purpose of evaluation.
In this FIRE 2021 shared task - "HASOC- Abusive and Threatening language detection in Urdu" the organizers propose an abusive language detection dataset in Urdu along with threatening language detection.
Hate speech is considered to be one of the major issues currently plaguing online social media.
Hate speech is regarded as one of the crucial issues plaguing the online social media.
Social media often acts as breeding grounds for different forms of offensive content.
We observe that users writing fear speech messages use various events and symbols to create the illusion of fear among the reader about a target community.
We also observe that models, which utilize the human rationales for training, perform better in reducing unintended bias towards target communities.
Ranked #1 on Hate Speech Detection on HateXplain
Hate speech detection is a challenging problem with most of the datasets available in only one language: English.
In this paper, we present our machine learning model, HateMonitor, developed for Hate Speech and Offensive Content Identification in Indo-European Languages (HASOC), a shared task at FIRE 2019.
With the online proliferation of hate speech, there is an urgent need for systems that can detect such harmful content.