textattack
There are 9 repositories under textattack topic.
QData/TextAttack-Search-Benchmark
EMNLP BlackBox NLP 2020: Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples
pradeepdev-1995/databalancer
Databalancer is the python library using in machine learning applications to balance the imbalanced text classification datasets before the model training.
QData/Reevaluating-NLP-Adversarial-Examples
EMNLP Findings 2020: Reevaluating Adversarial Examples in Natural Language
YoucefBYu/Job-Hunter-Project
In order to help students and job seekers in their journey of job hunting, from our experience we got the idea to start the project after the successful result of the first prototype that we build for personal use (massive job hunting). The app extract the data of given job (link of Linkedin or any job search platform) and use it to build a short insight that focus on the important key words, required Skills, level of education and information about the company. The extracted job data and the user data (Resume, Profile) will be used as input of the processing box (the sniper agency), It has Intelligente agent that use many tools and technique to produce results for example : The NLP text generator (we call it the philosopher) that produce a perfect motivation letter based on the input and some other predefined data. the second agent "The advisor" : it help the user to know the job skill set that he needs to master before applying to the job he is interested in, even we suggest online courses based on users rating, in general we use prediction models in this part.
QData/TextAttack-WebDemo
TextAttack Web Demo
VijayKalmath/AdversarialTraining_in_Distilation_Of_BERT
Implementation of Adversarial Training for BERT and BERT-Like Models and Analysis of effects of model compression on Robustness of a model
SameehanNS/Text_classifier_textattack
Medical dialogue classifier using DistilBERT model, implementing TextAttack along with adversarial training.
gaizkiaadeline/Multilabel-Hate-Speech-Classification-Using-LLM
A project focused on building a multilabel classification model to detect hate speech on social media using BERT and ALBERT pretrained models. It includes data augmentation techniques and hyperparameter tuning for optimal performance in identifying abusive content and hate speech.
zahradm/Thesis
Textual adversarial training with textattack