🤖 A PyTorch library of curated Transformer models and their composable components

Pytorch-Named-Entity-Recognition-with-transformers

How good is BERT ? Comparing BERT to other state-of-the-art approaches on a French sentiment analysis dataset

Anonymization of legal cases (Fr) based on Flair embeddings

Terminology extraction on ACTER using Transformer-based language models

The CEFR Level Classifier Project is a AI Streamlit-based application that utilizes a two-phase Camembert model to accurately classify texts into six CEFR language proficiency levels. This innovative tool offers user-friendly navigation for both training and text classification.

In this notebook, I attempted to create a script that utilizes pre-trained CamemBERT and VaderSentiment models to label the sentiment of a Quran Karim dataset in English and French. My goal was to accurately classify the sentiment of each text sample in the dataset.

This repository contains code for a fine-tuning experiment of CamemBERT, a French version of the BERT language model, on a portion of the FQuAD (French Question Answering Dataset) for Question Answering tasks.

Identification of causal discourse relations in French text using machine-translated training resources (MSc. Thesis, Tilburg University, NL)

Fine-tuning CamemBERT for French keywords extraction on custom dataset.

Just exploring NLP with 🤗 Transformers

Classification for the Rakuten challenge with PyTorch Lightning, Streamlit, fastAPI and Hydra

CYBIA est une IA française qui détermine la toxicité dans du texte 🇫🇷

Projet réalisé pour INSPIRE d'Article 1, mise en place d'algorithme de modération.

A codespace to run the French CamemBERT language model which is a great model for text prediction based on RoBERTa architecture through a minimalist web API.