Notebooks for fine-tuning a BERT model and training a LSTM model for financial QA

Notebook on finetuning BERT

Fine-tune BERT for sentiment analysis. I have done text preprocessing (special tokens, padding, and attention masks) and build a Sentiment Classifier using the amazing Transformers library by Hugging Face! I have train my model on kaggle notebook on gpu. The model give the accuracy of 95.14% on validation dataset.

Jupyter Notebooks consisting of various nlp tasks. (NLP role based interviews)

Sentiment analysis - Pytorch

Tutorial of Question Answering using SQuAD in English and Spanish with BERT and BiDAF.

This notebook leverages Transfer Learning Algorithms and standard NLP procedures to summarize a given paragraph meaningfully.

My Kaggle submission notebook - 83.8% Accuracy 🤟 (Top 8%)

NLP notebooks

The Sentiment analysis Attitude towards Covid-19 Vaccines in Africa Using Twitter data. All hackathon notebooks of the BIG DATA 2021 - Event held at TUK, sponsored by DARA Big Data, OAD and IDIA.

Notebook Projeto Boamente - NLP - ML - Bert - PyTorch - Projetos criados durante a execução do meu mestrado acadêmico UFDPar 2020-2022

Exploring a collection of Jupyter notebooks showcasing a variety of Natural Language Processing (NLP) projects.

The project utilizes Natural Language Processing (NLP) techniques to preprocess and analyze video transcripts, and employs a BERT + Bi-GRU model for text classification. The code is implemented in a Google Colab notebook.

Learned knowledge and techniques in Deep Learning and also related tools: Python, Pytorch, Jupyter Notebook, RNN, CNN, Reinforcement Learning, LSTM, BERT, Language Modeling

🗨️ This repository contains a collection of notebooks and resources for various NLP tasks using different architectures and frameworks.

Exploring Python-based projects

A Notebook that demonstrates how to use the BART Transformer model to perform title generation from abstracts.

NER Training on BERT model using Transformers on medical data, continual learning over 3 datasets; Notebooks and Scripts

This project fine-tunes the BERT model on Kaggle's spam-ham dataset to classify messages. It explores transformers and large language models (LLMs) in generative AI, with potential for customization to other sentiment analysis tasks. The repository includes a single Jupyter Notebook for complete code on preprocessing, training, and prediction.

This project explores methods to classify song lyrics by genre across two notebooks. In Notebook 1, various models (Transformer, LSTM, Random Forest) were tested, achieving accuracies up to 93.5%. Notebook 2 investigated Graph Neural Networks (GNNs) with TF-IDF and BERT embeddings, with the highest accuracy of 85.55% using GCN and BERT embeddings.