Università di Bologna, Facoltà di Ingegneria A.A. 2020/2021
This repository contains the final project of my NLP course. It aimed to create a question-answering system that, given a paragraph and a question regarding it, provides a single answer, which is obtained by selecting a span of text from the paragraph itself. The dataset was SQuAD (Stanford Question Answering Dataset) which contains 100,000+ question-answer pairs on 500+ articles.