Repository containing the project for the course on Business and Project Management at the University of Pisa (A.Y. 2022/2023) realized by Fabiano Pilia, Emanuele Tinghi and Matteo Dal Zotto.

In this we explore the large language models like Pegasus ,ERNIE and T5 Large

Finetuned FLAN-T5 to translate English to Hawaiian Pidgin

The project's goal is to use different Deep Learning techniques - T5 Transformer, Encoder & Decoder with BiLSTM models, and NLP to generate coherent summaries – to generate brief descriptions of news stories.

This project summarizes large text from any article to a smaller version without any loss in context. It uses the T5 Base transformer model.

A news headline generator finetuned on T5-base.

Fine-Tuning LLM for summarization in Portuguese (T5)

Fine-tuning the T5-base model using parts of the CNN/DailyMail dataset using PyTorch Lightning.

A NLP based summarizer which can summarize news article.

A RAG (Retrieval augmented generation)-based FAQ Chat-Bot, designed to operate within an organization's internal domain. - Jul 2023 - Oct 2023

German-to-English fine-tuned T5 base model with dependency-parsing enhancement.

A django application that allows you to summarize the content of a press article found by a user. It uses the T5 model for summarization, the LDA algorithm for topic modeling and Selenium to scrape the content of the linked article.

Institute Technical Summer Project -23/24

finetuning t5-base model for detoxifying texts.

This repository contains the code and outputs for the CS505: Natual Language Processing course project. The objective of this work is to explore the performance of different machine learning models in generating commit messages from changes in code.

Thesis scope: Train and Develop a Table-to-Text Transformer-based model for contextual summarization of tabular data. To achieve this T5-small , T5-base, Bart-base and Llama2 7B chat were finetuned on ToTTo and QTSumm. Regarding ToTTo, the models outperformed the benchmark.

The GitHub repository Information_Summarizer by Prathamesh Patil is a versatile tool built using Django, React, and Tailwind CSS. It allows users to generate summaries from various sources like plain text, PDFs, DOCX files, video transcripts, and website URLs, utilizing an advanced NLP model—Trained T5-base, trained on the abisee/cnn_dailymail 3.0.

This repository hosts an AI-powered chatbot using LLaMA 2 to promote constitutional literacy. It provides interactive answers on citizen rights, fundamental duties, and legal provisions. Built with Hugging Face Transformers, Streamlit, and a user-friendly UI, it simplifies legal knowledge for all. Contributions and improvements are welcome! 🚀

A resume matching tool. Finds the top 5 best matching resumes for each job description provided.

A web-based platform to manage and query databases without requiring an IDE or extensive knowledge of SQL, using natural language inputs for query generation.