Question and Answering telegram bot -- to increase productivity and efficiency within customer service related jobs.

Using State of Art transformers for text classification and deep CNNs for Image Classification

Applying zero-shot learning on classification task.

Deep learning for Natural Language Processing

Advanced RAG pipeline using Re-Ranking after initial retrieval

A sentiment analysing web application for customer reviews. Positive, Negative and Neutral opinions are highlighted.

I will perform a text classification tast using various Transformer like BERT, DistilBERT, ElLECTRA models, mostly from Huggingface community

Thesis Project

1. Fine-tune DistilBERT on NLI and dentify the some salient or toxic features that the model learnt. 2. Sample annotations techniques and production of silver label using (EDA and Back Translation).

🏥 Dr.Jarvis is a medical transcript classifier that helps patients to get their symptoms diagnosed in real-time on a Streamlit-powered web app. Trained by SVM, KNN, and Random Forest models of sklearn.

Deploying a pretrained distilBERT model with SageMaker

Kaggle Competition

A notebook for a medium article about text classification with Hugging Face DistilBert and Tensorflow 2.0

Distilbert trained on goemotions dataset using huggingface

Sentence Classification with BERT

A simple supervised learning solution to classifying candidates according to their professional seniority level (entry, mid, manager, cxo, etc.).

This repository contains the Romanian version of DistilBERT.

I performed sentiment analysis aimed at determining the sentiment of 50000 imDB movie reviews, whether they are positive, negative, or neutral. I employed various NLP approaches including lexicon based approaches, machine learning models, PLM models, and hybrid models, and assessed the performance on each type of model.