TextAttack
NLP robustness tester
A framework for creating and testing robust NLP models by generating adversarial examples and augmenting datasets.
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
3k stars
38 watching
401 forks
Language: Python
last commit: 6 months ago
Linked from 2 awesome lists
adversarial-attacksadversarial-examplesadversarial-machine-learningdata-augmentationmachine-learningnatural-language-processingnlpsecurity
ethicalml/awesome-production-machine-learning
keon/awesome-nlpRelated projects:
| Repository | Description | Stars |
|---|---|---|
 thunlp/openattack | A Python toolkit for generating adversarial examples to test the robustness of natural language processing models | 699 |
 explosion/spacy | Industrial-strength NLP library for Python and Cython | 30,459 |
 nltk/nltk | A comprehensive toolkit for natural language processing tasks in Python. | 13,694 |
 brightmart/text_classification | An NLP project offering various text classification models and techniques for deep learning exploration | 7,881 |
 huggingface/text-generation-inference | A toolkit for deploying and serving Large Language Models (LLMs) for high-performance text generation | 9,456 |
 jind11/textfooler | A tool for generating adversarial examples to attack text classification and inference models | 496 |
 deepset-ai/haystack | An AI orchestration framework to build customizable LLM applications with advanced retrieval methods. | 18,094 |
 minimaxir/textgenrnn | A Python module for creating character-level or word-level neural networks for text generation and training on various datasets | 4,944 |
 airbnb/artificial-adversary | A tool to generate adversarial text examples and test machine learning models against them | 399 |
 codertimo/bert-pytorch | An implementation of Google's 2018 BERT model in PyTorch, allowing pre-training and fine-tuning for natural language processing tasks | 6,251 |
 sherjilozair/char-rnn-tensorflow | A tool for training and sampling character-level language models using multi-layer recurrent neural networks | 2,643 |
 meta-llama/codellama | Provides inference code and tools for fine-tuning large language models, specifically designed for code generation tasks | 16,097 |
 stanfordnlp/stanza | A Python library for natural language processing tasks in many human languages. | 7,315 |
 chartbeat-labs/textacy | A Python library providing NLP tools and utilities built on top of spaCy for text processing and analysis. | 2,217 |
 sandeep42/anuvada | This is an open source PyTorch library providing tools and models to explain the predictions of deep neural networks for natural language processing tasks. | 19 |