EMNLP BlackBox NLP 2020: Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples

Databalancer is the python library using in machine learning applications to balance the imbalanced text classification datasets before the model training.

EMNLP Findings 2020: Reevaluating Adversarial Examples in Natural Language

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 shor…

TextAttack Web Demo

Implementation of Adversarial Training for BERT and BERT-Like Models and Analysis of effects of model compression on Robustness of a model

Textual adversarial training with textattack

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.

Medical dialogue classifier using DistilBERT model, implementing TextAttack along with adversarial training.

A collection of Python scripts demonstrating how to run various AI tasks locally using models from the Hugging Face Hub and the transformers library (along with related libraries like datasets, sentence-transformers, etc.). These examples cover a range of modalities including text, vision, and audio, showcasing different models and pipelines.