shahrukhx01 / bert-probeLinks
BERT Probe: A python package for probing attention based robustness to character and word based adversarial evaluation. Also, with recipes of implicit and explicit defenses against character-level attacks.
☆18Updated 3 years ago
Alternatives and similar repositories for bert-probe
Users that are interested in bert-probe are comparing it to the libraries listed below
Sorting:
- ☆19Updated 4 years ago
- [WIP] Behold, semantic-search, built over sentence-transformers to make it easy for search engineers to evaluate, optimise and deploy mod…☆15Updated 2 years ago
- A comprehensive tool for linguistic analysis of communities☆49Updated 3 years ago
- A multi-label text classifier to predict the subject areas of arXiv papers from their abstract bodies.☆17Updated 3 years ago
- ☆15Updated 4 years ago
- NLP Examples using the 🤗 libraries☆41Updated 4 years ago
- Low-code pre-built pipelines for experiments with huggingface/transformers for Data Scientists in a rush.☆16Updated 4 years ago
- Contains Colab Notebooks show cool use-cases of different GCP ML APIs.☆10Updated 4 years ago
- ☆13Updated 4 years ago
- Neural Search System on Arxiv AI/ML Papers☆54Updated 4 years ago
- NLP tool to extract emotional phrase from tweets 🤩☆40Updated 3 years ago
- Companion Repo for the Vision Language Modelling YouTube series - https://bit.ly/3PsbsC2 - by Prithivi Da. Open to PRs and collaborations☆14Updated 2 years ago
- (Silver medal - 60th place - Top 3%) Repository for the "Tweet Sentiment Extraction" Kaggle competition.☆10Updated 5 years ago
- An easy-to-use Python module that helps you to extract the BERT embeddings for a large text dataset (Bengali/English) efficiently.☆36Updated 2 years ago
- ☆11Updated 4 years ago
- Alternate Implementation for Zero Shot Text Classification: Instead of reframing NLI/XNLI, this reframes the text backbone of CLIP models…☆36Updated 3 years ago
- KitanaQA: Adversarial training and data augmentation for neural question-answering models☆56Updated 2 years ago
- Tokenization across languages. Useful as preprocessing for subword tokenization.☆22Updated 2 years ago
- Generating Training Data Made Easy☆43Updated 5 years ago
- Code for the paper: Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries☆19Updated 3 years ago
- This project shows how to build a simple handwriting recognizer in Keras with the IAM dataset.☆13Updated 3 years ago
- Streamlit demo app to demonstrate the features of transformers interpret with multiple models.☆25Updated 4 years ago
- ☆40Updated last year