In this project we have tried to do multi-label hate-speech classification in Bengali and Hindi language using fill-mask transformer models.
-
Updated
May 28, 2024 - Jupyter Notebook
In this project we have tried to do multi-label hate-speech classification in Bengali and Hindi language using fill-mask transformer models.
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.
SSA is a post-hoc explanation method by stereotypes and counter-stereotypes to assess social bias in hate speech classifiers
Hate Speech Detection Library for Python.
Knowledge-bound counter speech generation to challenge hate speech
HausaHate is a benchmark dataset for Hausa hate speech detection task. it was extracted from West African Facebook pages and comprises 2,000 comments annotated according to a binary class (offensive and non-offensive) and hate speech targets (race, gender and none).
Data and code for paper: Context-Aware Offensive Language Detection in Human-Chatbot Conversations
MetaHate: A Dataset for Unifying Efforts on Hate Speech Detection
A project implementing better evaluation scenarios for community models for malicious content detection, and meta-learning GNNs to achieve better downstream adaptation.
This repository contains the system description and the codes that we implemented for participating in EACL-2024 Shared Task-5.
This is a repository for AfriHate Project
Counter speech classification using adversarial training
A Brazilian Portuguese Text Offensiveness Analysis System
In this repository will be published some of the corpora that I helped to create or to annotate.
A Natural Portuguese Language Benchmark (Napolab) for the evaluation of language models.
Example dataset and prompt design of Korean Offensive language Machine Generation (K-OMG), published at IJCNLP-AACL 2023.
Joint work as part of a bachelor's thesis on utilizing a combination of NLP and CV methods in implementing multimodal approaches to combat hate speech in memes.
Intersectional bias in hate speech and abusive language datasets
Achieving Hate Speech Detection in a Low Resource Setting
The task is a binary classification problem to classify the given dataset into two classes namely Hate Offensive tweets (HOF) and Non-Hate Offensive tweets (NOT). The task appeared as Subtask-A in HASOC 2021. The dataset taken is sampled from Twitter. It consists of twitter posts in Hindi and Hinglish language.
Add a description, image, and links to the hate-speech topic page so that developers can more easily learn about it.
To associate your repository with the hate-speech topic, visit your repo's landing page and select "manage topics."