Toxic Comment Classification
12 papers with code • 4 benchmarks • 7 datasets
Benchmarks
These leaderboards are used to track progress in Toxic Comment Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Datasets
Civil Comments
Most implemented papers
Convolutional Neural Networks for Toxic Comment Classification
To justify this decision we choose to compare CNNs against the traditional bag-of-words approach for text analysis combined with a selection of algorithms proven to be very effective in text classification.
Is preprocessing of text really worth your time for online comment classification?
A large proportion of online comments present on public domains are constructive, however a significant proportion are toxic in nature.
Can We Achieve More with Less? Exploring Data Augmentation for Toxic Comment Classification
This paper tackles one of the greatest limitations in Machine Learning: Data Scarcity.
Trojaning Language Models for Fun and Profit
Recent years have witnessed the emergence of a new paradigm of building natural language processing (NLP) systems: general-purpose, pre-trained language models (LMs) are composed with simple downstream models and fine-tuned for a variety of NLP tasks.
From Hero to Zéroe: A Benchmark of Low-Level Adversarial Attacks
yannikbenz/zeroe
•
•
Adversarial attacks are label-preserving modifications to inputs of machine learning classifiers designed to fool machines but not humans.
From Hero to Z\'eroe: A Benchmark of Low-Level Adversarial Attacks
yannikbenz/zeroe
•
•
Asian Chapter of the Association for Computational Linguistics 2020
Adversarial attacks are label-preserving modifications to inputs of machine learning classifiers designed to fool machines but not humans.
FHAC at GermEval 2021: Identifying German toxic, engaging, and fact-claiming comments with ensemble learning
dslaborg/germeval2021
•
•
GermEval 2021
The availability of language representations learned by large pretrained neural network models (such as BERT and ELECTRA) has led to improvements in many downstream Natural Language Processing tasks in recent years.
A benchmark for toxic comment classification on Civil Comments dataset
Nigiva/hatespeech-detection-models
•
•
BiLSTM remains a good compromise between performance and inference time.
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Unlike these models, humans typically utilize external tools to cross-check and refine their initial content, like using a search engine for fact-checking, or a code interpreter for debugging.
Evaluating The Effectiveness of Capsule Neural Network in Toxic Comment Classification using Pre-trained BERT Embeddings
TashinAhmed/HATE
•
•
IEEE Region 10 International Conference TENCON 2023
By comparing the performance of CapsNet to that of other architectures, such as DistilBERT, Vanilla Neural Networks (VNN), and Convolutional Neural Networks (CNN), we were able to achieve an accuracy of 90. 44 %.
