This repository contains the code implementing and deploying content moderation for the Allay website.

OffenseEval2020 Competetion

Offensive Language Identification and Categorization

Translated abusive language dataset (En2Ko). Including OffensEval/AbusEval, CADD, Davidson et al., Waseem&Hovy.

The models developed by ASU_OPTO team as part of OffenseEval20 for Arabic tasks

MAD: A Multi-task Aggression Detection Framework

HASOC-Dravidian-CodeMix-FIRE 2021

Data and code for paper: Context-Aware Offensive Language Detection in Human-Chatbot Conversations

Tourettes

We utilized a pre-trained model to classify Arabic text. After conducting extensive research, we found that MarBERT was the best model for classifying Arabic offensive tweets. It focuses on dialectal Arabic (DA) and Modern Standard Arabic (MSA). The competition involves two shared sub-tasks: detecting whether a tweet is offensive or not; and det…

API para Detecção de comentários Ofensivos

a novel Romanian language dataset for offensive message detection with manually annotated comment from a local Romanian news website (stiri de cluj) into five classes

Using weak supervision to perform named entity recognition and offensive language detection on r/sg comments

Offend your friends and family! Generate scathing insults based on an edited dataset of insults scraped from various places around the web.

This rule will validate that a field isn't offensive.

This is NLP project of text multi-classification. My pre-trained model classify speech into three different categories offensive, hateful and neither.

SemEval 2019 - Shared Task 6: Offensive speech detection in tweets with several machine learning approaches with different features and several types of BERT

Supplementary material to the RANLP 2019 paper "Offence in Dialogues: A Corpus-Based Study"

Example dataset and prompt design of Korean Offensive language Machine Generation (K-OMG), published at IJCNLP-AACL 2023.