unitaryai / detoxify
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.
☆965Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for detoxify
- Catalog of abusive language data (PLoS 2020)☆304Updated 5 months ago
- NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations☆778Updated 6 months ago
- Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.☆1,294Updated last year
- Beyond Accuracy: Behavioral Testing of NLP models with CheckList☆2,010Updated 10 months ago
- TextAugment: Text Augmentation Library☆402Updated 9 months ago
- 🧹 Python package for text cleaning☆957Updated last year
- Robustness Gym is an evaluation toolkit for machine learning.☆440Updated 2 years ago
- A Neural Language Style Transfer framework to transfer natural language text smoothly between fine-grained language styles like formal/ca…☆479Updated 11 months ago
- skweak: A software toolkit for weak supervision applied to NLP tasks☆920Updated 2 months ago
- Repository for TweetEval☆357Updated 2 years ago
- Efficient few-shot learning with Sentence Transformers☆2,243Updated 2 months ago
- Happy Transformer makes it easy to fine-tune and perform inference with NLP Transformer models.☆519Updated 3 months ago
- ☆1,507Updated last year
- BLEURT is a metric for Natural Language Generation based on transfer learning.☆697Updated last year
- The implementation of DeBERTa☆1,993Updated last year
- A practical and feature-rich paraphrasing framework to augment human intents in text form to build robust NLU models for conversational e…☆879Updated 10 months ago
- Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.☆1,132Updated 9 months ago
- 🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy☆1,352Updated 5 months ago
- Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.☆189Updated last year
- Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conve…☆4,108Updated 5 months ago
- Compute Sentence Embeddings Fast!☆618Updated last year
- This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.☆280Updated 5 months ago
- Data augmentation for NLP☆4,457Updated 4 months ago
- A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coher…☆1,205Updated 10 months ago
- simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.☆388Updated last year
- Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the…☆1,985Updated 3 months ago
- The world's largest social media toxicity dataset.☆176Updated 2 years ago
- TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs…☆2,974Updated 3 months ago
- Keywords to Sentences☆447Updated last year
- Collection of papers and resources for data augmentation for NLP.☆828Updated 2 years ago