This repository contains the implementation of related article that was written as a part of Natural Language Processing course at the Faculty of Computer and Information Science at the University of Ljubljana.
The goal of the project is to prepare an english, slovene and multilingual english and slovene model for question answering system. Stanford Question Answering Dataset (SQuAD 2.0) is used as the main corpora. For training a slovene model, SQuAD corpora is automatically translated to Slovene, using the EK translator.
The repository contains the following folders:
article
contains the latex files and the article in pdfdata
contains the data used for teaching the modelsdocs
contains the files for generating documentation in Sphinxsrc
contains the code
Documentation is generated using Sphinx and is deployed on GitHub pages.